system

Abstract

We provide the system. [Solution] A means of collecting past sales information from each sales channel, A means of training a demand forecasting model based on collected sales information, A means of predicting future demand using a trained demand forecasting model, A means for calculating inventory allocation based on predicted demand and optimizing inventory, A means of monitoring sales information in real time and adjusting inventory allocation when there is a discrepancy between forecasts and actual sales, A system that includes this.

Description

【Technical Field】 【0001】 The technology of this disclosure relates to a system. 【Background Art】 【0002】 Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance. 【Prior Art Documents】 【Patent Documents】 【0003】 【Patent Document 1】 Japanese Patent Application Laid-Open No. 2022-180282 【Summary of the Invention】 【Problems to be Solved by the Invention】 【0004】 In modern inventory management, manually allocating inventory individually for each sales channel requires time and labor, and there is also a problem that the accuracy of demand forecasting is not sufficient. In particular, it is difficult for humans to grasp everything and manage optimal inventory while the characteristics and demand patterns of each sales channel are different. For this reason, cost increases due to inventory shortages or surpluses and losses of sales opportunities may occur. There is a need for an efficient and effective inventory management system to improve such a current situation. 【Means for Solving the Problems】 【0005】 This invention provides a system that enables more accurate demand forecasting by collecting past sales information from each sales channel and training a demand forecasting model based on this information. This system utilizes the trained model to predict future demand and calculates and optimizes inventory allocation based on the results. It also has a function to monitor sales information in real time and quickly adjust inventory allocation if there is a discrepancy between the forecast and actual sales. This enables efficient inventory management and efficient product supply. 【0006】 "Sales channels" refer to the routes a product takes from its manufacture to its delivery to the consumer, and include wholesalers, agents, retailers, etc. 【0007】 "Sales information" refers to data related to the sale of a product, specifically including information such as product ID, sales date, sales quantity, and price range. 【0008】 A "demand forecasting model" is a statistical or machine learning-based model used to predict future demand based on past sales data. 【0009】 "Inventory allocation" refers to the action or plan of deciding how much of a product to allocate to each sales channel or sales location based on projected demand. 【0010】 "Real-time" refers to the ability to instantly acquire and process the latest information, and usually means that events that occur are reflected within a very short time. 【0011】 "Inventory optimization" is a process of managing product inventory to ensure there is neither a shortage nor an excess, thereby minimizing costs and maximizing service levels. 【0012】 "Training a model" means using historical data to train a machine learning algorithm and improve its ability to make predictions based on new data. [Brief explanation of the drawing] 【0013】 [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention] 【0014】 Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings. 【0015】 First, the terms used in the following description will be explained. 【0016】 In the following embodiments, a processor with a reference number (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like. 【0017】 In the following embodiments, a RAM (Random Access Memory) with a reference number is a memory in which information is temporarily stored and is used as a work memory by the processor. 【0018】 In the following embodiments, a storage with a reference number is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like. 【0019】 In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark). 【0020】 In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or." 【0021】 [First Embodiment] 【0022】 Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment. 【0023】 As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server. 【0024】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0025】 The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52. 【0026】 The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input. 【0027】 The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor. 【0028】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54. 【0029】 Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14. 【0030】 As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30. 【0031】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0032】 In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0033】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal". 【0034】 This invention is a system for streamlining inventory management, aiming to automate demand forecasting and inventory allocation. The following describes embodiments for carrying out the invention based on the claims. 【0035】 This system primarily consists of a process where a server collects and analyzes sales information and then uses that information to forecast demand. Specifically, the server collects historical sales information from each sales channel. The collected information includes sales quantity, sales date, and number of units sold for each product. This allows for an understanding of the demand patterns for each sales channel. 【0036】 Next, the server analyzes the collected sales information to identify sales trends. For example, if a particular product is affected by seasonality or if sales are concentrated during a specific period, these characteristics are taken into account. This allows for the construction of a demand forecasting model. 【0037】 The server then uses a demand forecasting model to predict future demand. Based on the predicted demand, the server optimizes inventory allocation to each sales channel. This prevents excess inventory and shortages, enabling efficient inventory management. 【0038】 Furthermore, the server monitors sales in real time and quickly adjusts inventory allocation if a discrepancy is detected between forecasts and actual sales. For example, if demand suddenly surges due to a promotional event, the server immediately adjusts inventory to avoid shortages. In this way, the system of the present invention enables optimal inventory management for each sales channel. 【0039】 As a concrete example, in large retail stores, this system functions effectively to respond to regular promotions and seasonal fluctuations in demand. Based on historical data, the server predicts that certain products will sell well during the Christmas season and allocates inventory accordingly. As a result, the burden on the user (the manager) to manually adjust inventory is reduced, allowing them to carry out their work with greater efficiency. In this way, the system of the present invention achieves inventory management that is both efficient and accurate. 【0040】 The following describes the processing flow. 【0041】 Step 1: 【0042】 The server works in conjunction with the sales management system to periodically collect historical sales information from each sales channel. This sales information includes data such as product ID, sales date, and sales quantity. 【0043】 Step 2: 【0044】 The server stores the collected sales information in a database and performs initial data preprocessing. Specifically, it performs tasks such as imputing missing data and detecting and correcting outliers. This process creates a dataset suitable for analysis. 【0045】 Step 3: 【0046】 The server extracts features necessary for demand forecasting from sales information. These features include elements that are thought to influence demand, such as the day of the week, month, date of a specific event, and seasonal factors. 【0047】 Step 4: 【0048】 The server uses machine learning algorithms to train a demand forecasting model. Based on past sales data, patterns are input into the forecasting model to analyze future sales trends. At this stage, cross-validation is also performed to improve the accuracy of the model. 【0049】 Step 5: 【0050】 The server uses a trained model to predict future demand. It forecasts sales volume for each sales channel in the following week or month and calculates the required inventory based on that. 【0051】 Step 6: 【0052】 The server calculates inventory allocation based on the forecast results and distributes the optimal amount of inventory to each sales channel. This includes considering factors such as inventory costs and lead times. 【0053】 Step 7: 【0054】 The server monitors sales in real time. Based on the collected real-time sales data, it adjusts inventory allocation plans if there are discrepancies with forecasts. For example, it prepares for unexpected large-scale purchase events. 【0055】 Step 8: 【0056】 Users can review inventory allocation information provided by the server and request corrections from the supply chain as needed. They can also refer to reports generated by the server to improve their inventory policies. 【0057】 (Example 1) 【0058】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0059】 In inventory management, a key challenge is efficiently optimizing demand forecasting and inventory allocation using historical sales data. Currently, inventory adjustments are often done manually, leading to human error and inefficiencies. Furthermore, it is difficult to respond quickly to real-time demand fluctuations. 【0060】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0061】 In this invention, the server includes means for collecting historical sales data from each distribution channel, means for analyzing the collected sales data to identify sales trends, and means for constructing a demand forecasting model based on the identified sales trends. This enables accurate understanding of demand trends in each distribution channel, flexible response to differences between forecasts and actual distribution, and optimization of inventory allocation. 【0062】 "Distribution channels" refer to the entire sales channel involved in the process from when a product is produced until it reaches the consumer. 【0063】 "Sales data" refers to a collection of data that includes the quantity sold, unit price, sales date, and other related information for a product over a certain period. 【0064】 "Sales trends" refer to information that shows the tendencies and patterns related to product sales, based on analysis of past sales data. 【0065】 A "demand forecasting model" is a mathematical model constructed to predict future demand for a product based on past sales trends and external influencing factors. 【0066】 "Inventory allocation" is the process of efficiently allocating goods to various distribution channels and storage locations according to demand. 【0067】 "Optimization" is a methodology for making the most of resources under certain conditions to obtain the best possible results. 【0068】 "Real-time" is a concept that indicates that processing takes place almost simultaneously with real-world time. 【0069】 "Difference" refers to the difference between the predicted value and the actual value. 【0070】 This invention is a system that streamlines inventory management and optimizes inventory through demand forecasting. The following hardware and software are used to implement the system. 【0071】 The server plays a central role in automatically collecting sales data from each distribution channel and analyzing that data. Specifically, the server stores the data using a database management system, and uses programming languages ​​such as Python and R, along with their libraries (e.g., Pandas, NumPy), for data analysis. In addition, it uses machine learning frameworks such as TENSORFLOW® or PyTorch to build and train demand forecasting models. 【0072】 Users perform their tasks based on demand forecasts and inventory allocation plans provided by the server. By utilizing a generative AI model, users receive program advice to support their inventory management decisions. An example of a prompt to the AI ​​is: "Based on sales data for a specific product over the past three years, how can I forecast demand for the next season?" 【0073】 As a concrete example, in a retail setting, a server analyzes historical data prior to the Christmas season to predict increased demand for specific products. As a result, appropriate inventory allocation is made in advance, reducing the risk of stockouts and excess inventory. Inventory managers, who are the users of the system, can reduce the need for manual adjustments and improve operational efficiency. 【0074】 Thus, the system of the present invention plays a role in solving challenges in inventory management and supporting smooth business operations by accurately grasping sales trends and responding quickly to demand. 【0075】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0076】 Step 1: 【0077】 The server collects sales data from each distribution channel. The input is raw sales data obtained from the database of each distribution channel, which includes information such as product name, sales quantity, and sales date. This data is stored in the server's database management system and used as the basis for future analysis. 【0078】 Step 2: 【0079】 The server preprocesses the collected sales data. The input is the sales data collected in step 1. Specifically, the server performs data cleaning, including imputing missing values ​​and removing duplicate data. It uses the Python Pandas library to format the data, making it suitable for analysis and model building. The output is clean and formatted sales data. 【0080】 Step 3: 【0081】 The server analyzes pre-processed data to identify sales trends. The input is formatted sales data, and the server uses time series analysis to identify best-selling products and seasonal trends. It employs ARIMA models and other statistical methods for analysis. The output is data related to the identified sales trends. 【0082】 Step 4: 【0083】 The server builds a demand forecasting model based on sales trends. The input is the sales trend data obtained in step 3. The model is trained and learned using the machine learning framework TensorFlow. The server evaluates the model's performance and sets appropriate model parameters. The output is the constructed demand forecasting model. 【0084】 Step 5: 【0085】 The server uses a demand forecasting model to predict future demand. The input is new market data and trend information, and the model is executed to generate forecast data. The AI-generated forecast results are output, generating data indicating the required inventory levels for each distribution channel. 【0086】 Step 6: 【0087】 The server uses the forecast results to optimize inventory. The input is the forecast demand data obtained in step 5. The server uses optimization methods such as linear programming to calculate inventory allocation to each distribution channel. The output is the optimized inventory allocation plan. 【0088】 Step 7: 【0089】 The server monitors distribution information in real time and checks for discrepancies between forecasts and actual sales. The input is real-time sales data, monitored using a system like Kafka. If the server detects a discrepancy, it immediately readjusts inventory allocation to prevent shortages or surpluses. The output is the updated inventory allocation plan. 【0090】 (Application Example 1) 【0091】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0092】 In today's logistics and sales industries, streamlining inventory management and maximizing sales opportunities are major challenges. In particular, responding quickly to real-time demand fluctuations and allocating inventory appropriately is difficult. Furthermore, there is a need for systems that allow sales managers to accurately understand inventory levels and take swift action. 【0093】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0094】 In this invention, the server includes means for collecting historical sales information from each sales channel, means for training a demand forecasting model based on the collected sales information, and means for generating inventory management warnings using a mobile information processing device and notifying sales managers. This enables sales managers to grasp the inventory status in real time and adjust inventory allocation quickly and accurately. 【0095】 "Sales channels" refer to the entire distribution and sales route from the time a product reaches the consumer. 【0096】 A "demand forecasting model" is a model that uses statistical or machine learning methods to predict future sales volume and timing based on past sales data. 【0097】 "Inventory allocation" is the process of efficiently distributing inventory across multiple sales locations and warehouses. 【0098】 A "mobile information processing device" refers to a portable computing device, specifically a smartphone or tablet, that has the function of processing and displaying information. 【0099】 "Sales information" is a general term for various sales-related data, including sales quantity, sales date, and number of units sold for each product. 【0100】 "Features" are numerical data that represent the characteristics of the subject being analyzed in data analysis and machine learning, and are used as input for models. 【0101】 "Cleaning" refers to the process of removing and correcting noise and missing data, and preparing it in a format suitable for analysis. 【0102】 A "warning" refers to a notification or message that alerts the user when certain conditions occur. 【0103】 In implementing the present invention, the system is configured as follows: The server collects historical sales information from each sales channel and trains a demand forecasting model. Specifically, the server retrieves sales data from a database and performs preprocessing using a programming language such as Python. In this process, data cleaning is performed to remove noise and missing data and prepare the data for analysis. 【0104】 Next, the server uses machine learning libraries such as TensorFlow to build a demand forecasting model based on the cleaned data. This model accurately predicts future demand based on historical data and calculates the optimal inventory allocation. 【0105】 Users can use mobile information processing devices such as smartphones and tablets to check inventory status in real time. Here, a mobile application is developed using a cross-platform framework such as React Native. This application displays inventory allocation data and warnings sent from the server, providing sales managers with immediate action plans. 【0106】 As a concrete example, in a logistics center, if inventory of a specific product that sees increased demand during a certain season is likely to run low, a warning will be displayed on a mobile device. This warning allows sales managers to immediately arrange for additional stock and prevent shortages. 【0107】 To further utilize this system, a generative AI model can be used to generate prompts like the following, improving the accuracy of demand forecasting: "Based on sales data for a specific product during the Christmas season over the past three years, please tell me how to forecast next year's demand and optimize inventory allocation." 【0108】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0109】 Step 1: 【0110】 The server collects historical sales information from each sales channel. The input is a sales information database, and the output is the collected sales data. The data is retrieved via an API and includes sales quantity, sales date, number of units sold, etc. This prepares the system to understand the demand patterns of each sales channel. 【0111】 Step 2: 【0112】 The server cleans the collected sales information. The input is the data collected in step 1, and the output is clean data with noise and missing data removed. This process uses Python, and a data cleaning script is applied to prepare the data for analysis. 【0113】 Step 3: 【0114】 The server trains a demand forecasting model based on the cleaned data. The input is the cleaned data from step 2, and the output is the trained demand forecasting model. Here, TensorFlow is used to build a model that predicts future demand from historical data. 【0115】 Step 4: 【0116】 The server uses a trained model to predict future demand. The input is the trained model from step 3 and the latest sales data, and the output is predicted demand data. Based on this, highly accurate demand forecasts are made. 【0117】 Step 5: 【0118】 The server calculates inventory allocation based on predicted demand. The input is the demand forecast data from step 4, and the output is the optimized inventory allocation data. The inventory allocation algorithm is executed to determine the inventory allocation to each sales location. 【0119】 Step 6: 【0120】 The terminal displays inventory status and warnings on a mobile information processing device. Input is inventory allocation data from the server, and output is the screen display on the terminal. React Native is used to provide real-time inventory information visually to the user. 【0121】 Step 7: 【0122】 Users check inventory status via their devices and take action as needed. Input is the information displayed on the device screen, while output is the user's decisions and actions. Mobile applications allow for immediate execution of sales plans and replenishment orders. 【0123】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0124】 This invention provides a system that further optimizes demand forecasting and inventory allocation by combining an emotion engine that recognizes user emotions with an inventory management system. In this invention, a program running on a server analyzes user emotion information and improves the accuracy of the demand forecasting model based on that analysis. 【0125】 Specifically, the server first builds a demand forecasting model based on sales information collected from each sales channel. In addition, the emotion engine analyzes users' emotional states in real time, understanding the overall emotional trends of consumers from sources such as social media, customer reviews, and call center inquiries. This emotional data is input into the demand forecasting model, influencing future demand forecasts. 【0126】 Furthermore, the server can use user sentiment data analyzed by the sentiment engine to predict the effectiveness of sales campaigns and promotions. This allows for the creation of inventory allocation plans that anticipate user responses in advance, enabling inventory management with a buffer to cope with sudden fluctuations in demand. 【0127】 As a concrete example, if the server detects an increase in customer reviews for a particular product using its sentiment engine, it reflects the potential for increased demand for that product in its demand forecasting model and secures additional inventory in advance. This coordination between forecasting and inventory allocation allows retailers, as users, to always provide customers with the products they need. 【0128】 Furthermore, users can provide feedback on sales strategies through the emotion engine and interface. This allows for a direct understanding of how to meet consumer needs and strengthens the overall inventory management strategy. In this way, the present invention achieves a higher level of inventory optimization by combining user emotion analysis with traditional inventory management. 【0129】 The following describes the processing flow. 【0130】 Step 1: 【0131】 The server collects historical sales information from each sales channel and stores it in a database. The collected data includes sales volume, sales period, customer attributes, and more. 【0132】 Step 2: 【0133】 The server uses the collected sales information to create a demand forecasting model and uses machine learning algorithms to improve the accuracy of the forecast. 【0134】 Step 3: 【0135】 The server uses an emotion engine to analyze user emotions from various sources, such as social media and review sites. This allows for an understanding of consumers' emotional state towards a product. 【0136】 Step 4: 【0137】 The server integrates sentiment data into the demand forecasting model and applies sentiment-based adjustments to further improve the accuracy of demand forecasts. The model reflects increases in positive sentiment towards the product in the forecasted demand. 【0138】 Step 5: 【0139】 The server calculates the optimal inventory allocation based on future demand forecasts and instructs each sales channel to apply it. Inventory allocation follows the results calculated from predicted demand and market sentiment trends. 【0140】 Step 6: 【0141】 The server monitors sales in real time and dynamically readjusts inventory allocation and distribution plans if a discrepancy is found between forecasts and actual sales. Sentiment data fluctuations are also re-evaluated during this process. 【0142】 Step 7: 【0143】 Users review reports generated by the server and incorporate them into sales strategies and inventory management policies. The results of sentiment analysis performed by the server are also used in strategic decision-making. 【0144】 Step 8: 【0145】 The device receives user feedback as needed and feeds that feedback back into both the emotion engine and the demand forecasting model. This improves the overall adaptability of the system. 【0146】 (Example 2) 【0147】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal." 【0148】 Traditional inventory management systems relied on sales data for demand forecasting, but they failed to adequately consider consumer sentiment and market trends, making it difficult to respond flexibly to fluctuations in demand. Furthermore, discrepancies between forecasting models and actual sales data could occur, hindering the optimization of inventory allocation. Therefore, there is a need for more accurate and flexible inventory management. 【0149】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0150】 In this invention, the server includes means for collecting past transaction information from each supply route, means for training a demand forecasting algorithm based on the collected transaction information, and means for analyzing user sentiment information and reflecting the analysis results in the demand forecasting algorithm. By incorporating the emotional state of consumers into the demand forecast, it becomes possible to achieve more accurate demand forecasting and optimization of inventory allocation. 【0151】 "Supply chain" refers to the entire path a product takes from the manufacturer or distribution center to the consumer, and includes wholesalers, retailers, and online sales platforms. 【0152】 "Transaction information" refers to detailed data about the sale of a product, including information such as sales quantity, sales price, transaction date and time, and transaction region. 【0153】 A "demand forecasting algorithm" refers to a computational method or model used to predict future demand for a product based on collected data, enabling companies to rationally plan the necessary inventory and production volumes. 【0154】 "Emotional information" refers to data that indicates consumers' emotional states and emotional trends in the market, and is obtained from sources such as social media posts, customer reviews, and inquiries. 【0155】 "Learning" refers to the process by which an algorithm finds patterns and rules from the provided data and automatically updates the model to make highly accurate predictions. 【0156】 "Product allocation" refers to the process of appropriately allocating and supplying products to each sales location based on demand forecasts, and is an important activity for achieving efficient inventory management. 【0157】 "Assets" refer to all of the goods, property, and intellectual property owned by a company, and the management and optimization of these improve the operational efficiency of the company. 【0158】 "Discrepancy" refers to the difference between predicted demand and actual observed sales, and resolving this discrepancy leads to improved accuracy in inventory management. 【0159】 The embodiments for carrying out the invention are shown below. 【0160】 In this invention, the server integrates an inventory management system with an emotion engine that recognizes user emotions to achieve more accurate demand forecasting and optimized inventory allocation. Specifically, the server collects transaction information from each supply route and uses this information to train a demand forecasting algorithm. For training, it uses Python libraries for data analysis such as Pandas and Scikit-learn. Furthermore, it utilizes the emotion engine to analyze consumer emotion information in real time from various sources such as social media, customer reviews, and call center inquiries. For this analysis, it uses natural language processing libraries such as TensorFlow and NLTK. 【0161】 After transaction and sentiment data are analyzed, the server incorporates the sentiment data into a demand forecasting algorithm to predict future demand. Based on this forecast, the server adjusts product allocation to support efficient inventory management. The server also has the ability to constantly monitor the forecasting model and actual transaction data, and adjust product allocation as needed. 【0162】 For example, if consumer sentiment information about a particular cosmetic product rapidly gains positive reviews on social media, the server can use that data to predict the increase in demand and meet consumer needs by securing additional inventory in advance. In this way, retailers, as users, can provide consumers with the necessary products in a timely manner without missing sales opportunities. 【0163】 An example of a prompt to input into the generating AI model might be, "How can we build a demand forecasting model to optimize inventory allocation for each store?" This prompt allows for the development of new algorithms to improve demand forecasting accuracy. 【0164】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0165】 Step 1: 【0166】 The server collects historical transaction information from each supply chain. As input, it accesses online store and physical store sales databases to obtain detailed data such as product names, sales quantities, and sales periods. This data is extracted through database queries and stored on the server. As output, the collected transaction information is organized into usable datasets. 【0167】 Step 2: 【0168】 The server trains a demand forecasting algorithm based on the collected transaction information. The transaction data generated in Step 1 is used as input. The server uses libraries such as Pandas and Scikit-learn to analyze this data, extract features, and build a model suitable for demand forecasting. The trained demand forecasting model is obtained as output, which is useful for future demand forecasting. 【0169】 Step 3: 【0170】 The server analyzes user emotional information using an emotion engine. Inputs include social media posts, customer reviews, and call center inquiry logs. The server utilizes natural language processing techniques to score emotions as positive, negative, or neutral. TensorFlow and NLTK are used for this analysis. The output generates data indicating the user's emotional tendencies. 【0171】 Step 4: 【0172】 The server integrates the analyzed sentiment information into the demand forecasting model. The demand forecasting model obtained in step 2 and the sentiment data from step 3 are used as input. The server adjusts the model parameters to perform a more accurate demand forecast that reflects the sentiment data. The output is a demand forecast result that takes sentiment information into account. 【0173】 Step 5: 【0174】 The server optimizes product allocation and manages assets based on demand forecast results. The demand forecast results obtained in step 4 are used as input. The server calculates inventory reallocation and issues instructions to maintain optimal inventory levels at each sales point. The output is optimized product allocation, streamlining inventory management. 【0175】 Step 6: 【0176】 The user receives forecast results and sales strategy feedback from the server. The input consists of forecast data and analysis results generated by the server. The user uses this information to adjust sales activities and campaign plans. The output is that the user's sales strategies are aligned with market demand, maximizing sales opportunities. 【0177】 (Application Example 2) 【0178】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal". 【0179】 Modern inventory management systems generally forecast demand and manage inventory based on historical sales data, but they fail to take into account customer sentiment and the elusive trends of the market, making it difficult to respond immediately to fluctuations in demand. This increases the risk of oversupply or undersupply, hindering efficient inventory management. Furthermore, the lack of means to predict the effectiveness of sales strategies means that promotions and campaigns are not being adequately optimized. 【0180】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0181】 In this invention, the server includes means for collecting historical sales data from each supply route, means for training a demand forecasting structure based on the collected sales data, and means for analyzing user sentiment data and integrating that sentiment data into the demand forecasting structure to improve the accuracy of demand. This enables advanced inventory management that incorporates customer sentiment and market trends. Furthermore, it enables immediate response to demand fluctuations through real-time monitoring of sales data and adjustment of supply allocation. 【0182】 "Supply route" refers to the concept of the path by which goods or services are delivered from the manufacturer or supplier to the consumer. 【0183】 "Sales data" refers to information that shows how much of a product or service was sold within a specific period, and typically includes quantity, price, and purchase date. 【0184】 A "demand forecast structure" refers to a statistical or computational model used to predict future demand levels based on historical data and market information. 【0185】 "Sentimental data" refers to information that reflects consumers' emotions and opinions, and is typically collected from sources such as social media, reviews, and survey results. 【0186】 "Inventory management" refers to the activities undertaken by companies and organizations to efficiently manage their inventory of goods and materials and to optimize the balance between supply and demand. 【0187】 A "sales strategy" refers to a plan or policy for effectively selling a product or service based on market and customer needs. 【0188】 This invention is an inventory management system that integrates sentiment data to improve demand forecasting. The system is implemented using a server, user terminals, and market information as a data source. 【0189】 The server collects historical sales data from each supply chain and uses this data to build a demand forecasting structure. The collected data undergoes a data cleaning process to prepare it for model training. During this process, data processing is performed using libraries such as Python's pandas and numpy. 【0190】 Next, natural language processing is performed to analyze user sentiment data. Sentiment data is obtained from social media posts and customer reviews, and positive / negative sentiment tendencies are evaluated using NLTK and TextBlob. This sentiment information is integrated as a feed into the demand forecasting structure, contributing to improving the accuracy of the model. 【0191】 The terminal receives recommended inventory allocations based on these analysis results, enabling real-time supply adjustments. It integrates with cloud computing services (e.g., AWS® and Google® Cloud) to perform dynamic data processing. 【0192】 As a concrete example, the system detects when a particular fashion brand gains attention on social media and predicts a surge in demand for that product category. If it determines there is a risk of inventory shortages, it immediately adjusts the supply allocation to increase the stock of the relevant product. 【0193】 The generative AI model can analyze sentiment data using the following prompt statements. 【0194】 "Collect recent tweets related to a specific product and analyze their sentiment scores." 【0195】 In this way, the server enables advanced inventory management to respond quickly to fluctuations in demand. 【0196】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0197】 Step 1: 【0198】 The server collects historical sales data from each supply route. Inputs are database and sensor data from the supply route, and output is the collected raw data. Sales data is extracted from the database using SQL queries and stored in CSV or JSON format. 【0199】 Step 2: 【0200】 The server cleans the collected sales data and prepares it in a format suitable for training the demand forecasting model. The input is the raw data obtained in step 1, and the output is the prepared dataset. Missing value handling and outlier detection are performed using the Python pandas library. 【0201】 Step 3: 【0202】 The server collects user sentiment data from social media and customer reviews, and uses natural language processing to evaluate sentiment tendencies. The input is text from social media posts and reviews, and the output is a sentiment score. NLTK and TextBlob are used to analyze the text and calculate positive and negative scores. 【0203】 Step 4: 【0204】 The server integrates sentiment data into a demand forecasting model to improve its accuracy. The input is a prepared dataset and sentiment scores, and the output is an enhanced demand forecasting model. The machine learning library scikit-learn is used to retrain the model. 【0205】 Step 5: 【0206】 The terminal receives recommended inventory allocations based on an enhanced demand forecasting model. The input is forecast data from the enhanced demand forecasting model, and the output is the recommended inventory allocation. It communicates with the cloud system via a real-time API to retrieve the recommended allocation. 【0207】 Step 6: 【0208】 The user reviews the recommended inventory allocation and supply adjustment notifications on the terminal and makes adjustments as needed. The input is the recommended allocation from step 5, and the output is the actual inventory adjustment result. The user reviews the information provided through the terminal's UI and makes adjustments manually. 【0209】 The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data. 【0210】 Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0211】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14. 【0212】 [Second Embodiment] 【0213】 Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment. 【0214】 As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server. 【0215】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0216】 The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52. 【0217】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0218】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0219】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0220】 Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0221】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0222】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0223】 In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0224】 Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0225】 This invention is a system for streamlining inventory management, aiming to automate demand forecasting and inventory allocation. The following describes embodiments for carrying out the invention based on the claims. 【0226】 This system primarily consists of a process where a server collects and analyzes sales information and then uses that information to forecast demand. Specifically, the server collects historical sales information from each sales channel. The collected information includes sales quantity, sales date, and number of units sold for each product. This allows for an understanding of the demand patterns for each sales channel. 【0227】 Next, the server analyzes the collected sales information to identify sales trends. For example, if a particular product is affected by seasonality or if sales are concentrated during a specific period, these characteristics are taken into account. This allows for the construction of a demand forecasting model. 【0228】 The server then uses a demand forecasting model to predict future demand. Based on the predicted demand, the server optimizes inventory allocation to each sales channel. This prevents excess inventory and shortages, enabling efficient inventory management. 【0229】 Furthermore, the server monitors sales in real time and quickly adjusts inventory allocation if a discrepancy is detected between forecasts and actual sales. For example, if demand suddenly surges due to a promotional event, the server immediately adjusts inventory to avoid shortages. In this way, the system of the present invention enables optimal inventory management for each sales channel. 【0230】 As a concrete example, in large retail stores, this system functions effectively to respond to regular promotions and seasonal fluctuations in demand. Based on historical data, the server predicts that certain products will sell well during the Christmas season and allocates inventory accordingly. As a result, the burden on the user (the manager) to manually adjust inventory is reduced, allowing them to carry out their work with greater efficiency. In this way, the system of the present invention achieves inventory management that is both efficient and accurate. 【0231】 The following describes the processing flow. 【0232】 Step 1: 【0233】 The server works in conjunction with the sales management system to periodically collect historical sales information from each sales channel. This sales information includes data such as product ID, sales date, and sales quantity. 【0234】 Step 2: 【0235】 The server stores the collected sales information in a database and performs initial data preprocessing. Specifically, it performs tasks such as imputing missing data and detecting and correcting outliers. This process creates a dataset suitable for analysis. 【0236】 Step 3: 【0237】 The server extracts features necessary for demand forecasting from sales information. These features include elements that are thought to influence demand, such as the day of the week, month, date of a specific event, and seasonal factors. 【0238】 Step 4: 【0239】 The server uses machine learning algorithms to train a demand forecasting model. Based on past sales data, patterns are input into the forecasting model to analyze future sales trends. At this stage, cross-validation is also performed to improve the accuracy of the model. 【0240】 Step 5: 【0241】 The server uses a trained model to predict future demand. It forecasts sales volume for each sales channel in the following week or month and calculates the required inventory based on that. 【0242】 Step 6: 【0243】 The server calculates inventory allocation based on the forecast results and distributes the optimal amount of inventory to each sales channel. This includes considering factors such as inventory costs and lead times. 【0244】 Step 7: 【0245】 The server monitors sales in real time. Based on the collected real-time sales data, it adjusts inventory allocation plans if there are discrepancies with forecasts. For example, it prepares for unexpected large-scale purchase events. 【0246】 Step 8: 【0247】 Users can review inventory allocation information provided by the server and request corrections from the supply chain as needed. They can also refer to reports generated by the server to improve their inventory policies. 【0248】 (Example 1) 【0249】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0250】 In inventory management, a key challenge is efficiently optimizing demand forecasting and inventory allocation using historical sales data. Currently, inventory adjustments are often done manually, leading to human error and inefficiencies. Furthermore, it is difficult to respond quickly to real-time demand fluctuations. 【0251】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0252】 In this invention, the server includes means for collecting historical sales data from each distribution channel, means for analyzing the collected sales data to identify sales trends, and means for constructing a demand forecasting model based on the identified sales trends. This enables accurate understanding of demand trends in each distribution channel, flexible response to differences between forecasts and actual distribution, and optimization of inventory allocation. 【0253】 "Distribution channels" refer to the entire sales channel involved in the process from when a product is produced until it reaches the consumer. 【0254】 "Sales data" refers to a collection of data that includes the quantity sold, unit price, sales date, and other related information for a product over a certain period. 【0255】 "Sales trends" refer to information that shows the tendencies and patterns related to product sales, based on analysis of past sales data. 【0256】 A "demand forecasting model" is a mathematical model constructed to predict future demand for a product based on past sales trends and external influencing factors. 【0257】 "Inventory allocation" is the process of efficiently allocating goods to various distribution channels and storage locations according to demand. 【0258】 "Optimization" is a methodology for making the most of resources under certain conditions to obtain the best possible results. 【0259】 "Real-time" is a concept that indicates that processing takes place almost simultaneously with real-world time. 【0260】 "Difference" refers to the difference between the predicted value and the actual value. 【0261】 This invention is a system that streamlines inventory management and optimizes inventory through demand forecasting. The following hardware and software are used to implement the system. 【0262】 The server plays a central role in automatically collecting sales data from each distribution channel and analyzing that data. Specifically, the server stores the data using a database management system, and uses programming languages ​​such as Python and R, along with their libraries (e.g., Pandas, NumPy), for data analysis. It also uses TensorFlow or PyTorch as a machine learning framework to build and train demand forecasting models. 【0263】 Users perform their tasks based on demand forecasts and inventory allocation plans provided by the server. By utilizing a generative AI model, users receive program advice to support their inventory management decisions. An example of a prompt to the AI ​​is: "Based on sales data for a specific product over the past three years, how can I forecast demand for the next season?" 【0264】 As a concrete example, in a retail setting, a server analyzes historical data prior to the Christmas season to predict increased demand for specific products. As a result, appropriate inventory allocation is made in advance, reducing the risk of stockouts and excess inventory. Inventory managers, who are the users of the system, can reduce the need for manual adjustments and improve operational efficiency. 【0265】 Thus, the system of the present invention plays a role in solving challenges in inventory management and supporting smooth business operations by accurately grasping sales trends and responding quickly to demand. 【0266】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0267】 Step 1: 【0268】 The server collects sales data from each distribution channel. The input is raw sales data obtained from the database of each distribution channel, which includes information such as product name, sales quantity, and sales date. This data is stored in the server's database management system and used as the basis for future analysis. 【0269】 Step 2: 【0270】 The server preprocesses the collected sales data. The input is the sales data collected in step 1. Specifically, the server performs data cleaning, including imputing missing values ​​and removing duplicate data. It uses the Python Pandas library to format the data, making it suitable for analysis and model building. The output is clean and formatted sales data. 【0271】 Step 3: 【0272】 The server analyzes pre-processed data to identify sales trends. The input is formatted sales data, and the server uses time series analysis to identify best-selling products and seasonal trends. It employs ARIMA models and other statistical methods for analysis. The output is data related to the identified sales trends. 【0273】 Step 4: 【0274】 The server builds a demand forecasting model based on sales trends. The input is the sales trend data obtained in step 3. The model is trained and learned using the machine learning framework TensorFlow. The server evaluates the model's performance and sets appropriate model parameters. The output is the constructed demand forecasting model. 【0275】 Step 5: 【0276】 The server uses a demand forecasting model to predict future demand. The input is new market data and trend information, and the model is executed to generate forecast data. The AI-generated forecast results are output, generating data indicating the required inventory levels for each distribution channel. 【0277】 Step 6: 【0278】 The server uses the forecast results to optimize inventory. The input is the forecast demand data obtained in step 5. The server uses optimization methods such as linear programming to calculate inventory allocation to each distribution channel. The output is the optimized inventory allocation plan. 【0279】 Step 7: 【0280】 The server monitors distribution information in real time and checks for discrepancies between forecasts and actual sales. The input is real-time sales data, monitored using a system like Kafka. If the server detects a discrepancy, it immediately readjusts inventory allocation to prevent shortages or surpluses. The output is the updated inventory allocation plan. 【0281】 (Application Example 1) 【0282】 Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart glasses 214 are referred to as a "terminal". 【0283】 In the modern logistics and sales industries, improving inventory management efficiency and maximizing sales opportunities are major issues. In particular, it is difficult to quickly respond to real-time demand fluctuations and perform appropriate inventory allocation. There is also a need for a system that enables sales managers to accurately grasp inventory status and promptly take countermeasures. 【0284】 The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0285】 In this invention, the server includes means for collecting past sales information from each sales route, means for learning a demand prediction model based on the collected sales information, and means for generating an inventory management warning using a mobile information processing device and notifying the sales manager. As a result, the sales manager can grasp the inventory status in real time and can quickly and accurately adjust inventory allocation. 【0286】 The "sales route" refers to the entire distribution and sales route until the product reaches the consumer. 【0287】 The "demand prediction model" is a model using statistical or machine learning methods for predicting future sales quantities and times based on past sales data. 【0288】 "Inventory allocation" is a process of efficiently allocating inventory to multiple sales bases and warehouses. 【0289】 The "mobile information processing device" refers to a portable computing device, specifically a smartphone or a tablet, and is a device having a function of processing and displaying information. 【0290】 "Sales information" is a general term for various sales-related data, including sales quantity, sales date, and number of units sold for each product. 【0291】 "Features" are numerical data that represent the characteristics of the subject being analyzed in data analysis and machine learning, and are used as input for models. 【0292】 "Cleaning" refers to the process of removing and correcting noise and missing data, and preparing it in a format suitable for analysis. 【0293】 A "warning" refers to a notification or message that alerts the user when certain conditions occur. 【0294】 In implementing the present invention, the system is configured as follows: The server collects historical sales information from each sales channel and trains a demand forecasting model. Specifically, the server retrieves sales data from a database and performs preprocessing using a programming language such as Python. In this process, data cleaning is performed to remove noise and missing data and prepare the data for analysis. 【0295】 Next, the server uses machine learning libraries such as TensorFlow to build a demand forecasting model based on the cleaned data. This model accurately predicts future demand based on historical data and calculates the optimal inventory allocation. 【0296】 Users can use mobile information processing devices such as smartphones and tablets to check inventory status in real time. Here, a mobile application is developed using a cross-platform framework such as React Native. This application displays inventory allocation data and warnings sent from the server, providing sales managers with immediate action plans. 【0297】 As a concrete example, in a logistics center, if inventory of a specific product that sees increased demand during a certain season is likely to run low, a warning will be displayed on a mobile device. This warning allows sales managers to immediately arrange for additional stock and prevent shortages. 【0298】 To further utilize this system, a generative AI model can be used to generate prompts like the following, improving the accuracy of demand forecasting: "Based on sales data for a specific product during the Christmas season over the past three years, please tell me how to forecast next year's demand and optimize inventory allocation." 【0299】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0300】 Step 1: 【0301】 The server collects historical sales information from each sales channel. The input is a sales information database, and the output is the collected sales data. The data is retrieved via an API and includes sales quantity, sales date, number of units sold, etc. This prepares the system to understand the demand patterns of each sales channel. 【0302】 Step 2: 【0303】 The server cleans the collected sales information. The input is the data collected in step 1, and the output is clean data with noise and missing data removed. This process uses Python, and a data cleaning script is applied to prepare the data for analysis. 【0304】 Step 3: 【0305】 The server trains a demand forecasting model based on the cleaned data. The input is the cleaned data from step 2, and the output is the trained demand forecasting model. Here, TensorFlow is used to build a model that predicts future demand from historical data. 【0306】 Step 4: 【0307】 The server uses the learned model to predict future demand. The inputs are the learned model from Step 3 and the latest sales data, and the output is the predicted demand data. Based on this, a highly accurate demand prediction is made. 【0308】 Step 5: 【0309】 The server calculates inventory allocation based on the predicted demand. The input is the demand prediction data from Step 4, and the output is the optimized inventory allocation data. The inventory allocation algorithm is executed, and the inventory allocation to each sales base is determined. 【0310】 Step 6: 【0311】 The terminal displays the inventory status and warnings on the mobile information processing device. The input is the inventory allocation data from the server, and the output is the screen display on the terminal. Using React Native, the inventory information is visually provided to the user in real time. 【0312】 Step 7: 【0313】 The user checks the inventory status through the terminal and takes measures as necessary. The input is the screen display information of the terminal, and the output is the user's decision-making and actions. Using the mobile application, the sales plan and replenishment arrangements can be executed immediately. 【0314】 Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform specific processing using the user's emotion. 【0315】 This invention provides a system that further optimizes demand forecasting and inventory allocation by combining an emotion engine that recognizes user emotions with an inventory management system. In this invention, a program running on a server analyzes user emotion information and improves the accuracy of the demand forecasting model based on that analysis. 【0316】 Specifically, the server first builds a demand forecasting model based on sales information collected from each sales channel. In addition, the emotion engine analyzes users' emotional states in real time, understanding the overall emotional trends of consumers from sources such as social media, customer reviews, and call center inquiries. This emotional data is input into the demand forecasting model, influencing future demand forecasts. 【0317】 Furthermore, the server can use user sentiment data analyzed by the sentiment engine to predict the effectiveness of sales campaigns and promotions. This allows for the creation of inventory allocation plans that anticipate user responses in advance, enabling inventory management with a buffer to cope with sudden fluctuations in demand. 【0318】 As a concrete example, if the server detects an increase in customer reviews for a particular product using its sentiment engine, it reflects the potential for increased demand for that product in its demand forecasting model and secures additional inventory in advance. This coordination between forecasting and inventory allocation allows retailers, as users, to always provide customers with the products they need. 【0319】 Furthermore, users can provide feedback on sales strategies through the emotion engine and interface. This allows for a direct understanding of how to meet consumer needs and strengthens the overall inventory management strategy. In this way, the present invention achieves a higher level of inventory optimization by combining user emotion analysis with traditional inventory management. 【0320】 The following describes the processing flow. 【0321】 Step 1: 【0322】 The server collects historical sales information from each sales channel and stores it in a database. The collected data includes sales volume, sales period, customer attributes, and more. 【0323】 Step 2: 【0324】 The server uses the collected sales information to create a demand forecasting model and uses machine learning algorithms to improve the accuracy of the forecast. 【0325】 Step 3: 【0326】 The server uses an emotion engine to analyze user emotions from various sources, such as social media and review sites. This allows for an understanding of consumers' emotional state towards a product. 【0327】 Step 4: 【0328】 The server integrates sentiment data into the demand forecasting model and applies sentiment-based adjustments to further improve the accuracy of demand forecasts. The model reflects increases in positive sentiment towards the product in the forecasted demand. 【0329】 Step 5: 【0330】 The server calculates the optimal inventory allocation based on future demand forecasts and instructs each sales channel to apply it. Inventory allocation follows the results calculated from predicted demand and market sentiment trends. 【0331】 Step 6: 【0332】 The server monitors sales in real time and dynamically readjusts inventory allocation and distribution plans if a discrepancy is found between forecasts and actual sales. Sentiment data fluctuations are also re-evaluated during this process. 【0333】 Step 7: 【0334】 Users review reports generated by the server and incorporate them into sales strategies and inventory management policies. The results of sentiment analysis performed by the server are also used in strategic decision-making. 【0335】 Step 8: 【0336】 The device receives user feedback as needed and feeds that feedback back into both the emotion engine and the demand forecasting model. This improves the overall adaptability of the system. 【0337】 (Example 2) 【0338】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal". 【0339】 Traditional inventory management systems relied on sales data for demand forecasting, but they failed to adequately consider consumer sentiment and market trends, making it difficult to respond flexibly to fluctuations in demand. Furthermore, discrepancies between forecasting models and actual sales data could occur, hindering the optimization of inventory allocation. Therefore, there is a need for more accurate and flexible inventory management. 【0340】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0341】 In this invention, the server includes means for collecting past transaction information from each supply route, means for training a demand forecasting algorithm based on the collected transaction information, and means for analyzing user sentiment information and reflecting the analysis results in the demand forecasting algorithm. By incorporating the emotional state of consumers into the demand forecast, it becomes possible to achieve more accurate demand forecasting and optimization of inventory allocation. 【0342】 "Supply chain" refers to the entire path a product takes from the manufacturer or distribution center to the consumer, and includes wholesalers, retailers, and online sales platforms. 【0343】 "Transaction information" refers to detailed data about the sale of a product, including information such as sales quantity, sales price, transaction date and time, and transaction region. 【0344】 A "demand forecasting algorithm" refers to a computational method or model used to predict future demand for a product based on collected data, enabling companies to rationally plan the necessary inventory and production volumes. 【0345】 "Emotional information" refers to data that indicates consumers' emotional states and emotional trends in the market, and is obtained from sources such as social media posts, customer reviews, and inquiries. 【0346】 "Learning" refers to the process by which an algorithm finds patterns and rules from the provided data and automatically updates the model to make highly accurate predictions. 【0347】 "Product allocation" refers to the process of appropriately allocating and supplying products to each sales location based on demand forecasts, and is an important activity for achieving efficient inventory management. 【0348】 "Assets" refer to all of the goods, property, and intellectual property owned by a company, and the management and optimization of these improve the operational efficiency of the company. 【0349】 "Discrepancy" refers to the difference between predicted demand and actual observed sales, and resolving this discrepancy leads to improved accuracy in inventory management. 【0350】 The embodiments for carrying out the invention are shown below. 【0351】 In this invention, the server integrates an inventory management system with an emotion engine that recognizes user emotions to achieve more accurate demand forecasting and optimized inventory allocation. Specifically, the server collects transaction information from each supply route and uses this information to train a demand forecasting algorithm. For training, it uses Python libraries for data analysis such as Pandas and Scikit-learn. Furthermore, it utilizes the emotion engine to analyze consumer emotion information in real time from various sources such as social media, customer reviews, and call center inquiries. For this analysis, it uses natural language processing libraries such as TensorFlow and NLTK. 【0352】 After transaction and sentiment data are analyzed, the server incorporates the sentiment data into a demand forecasting algorithm to predict future demand. Based on this forecast, the server adjusts product allocation to support efficient inventory management. The server also has the ability to constantly monitor the forecasting model and actual transaction data, and adjust product allocation as needed. 【0353】 For example, if consumer sentiment information about a particular cosmetic product rapidly gains positive reviews on social media, the server can use that data to predict the increase in demand and meet consumer needs by securing additional inventory in advance. In this way, retailers, as users, can provide consumers with the necessary products in a timely manner without missing sales opportunities. 【0354】 An example of a prompt to input into the generating AI model might be, "How can we build a demand forecasting model to optimize inventory allocation for each store?" This prompt allows for the development of new algorithms to improve demand forecasting accuracy. 【0355】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0356】 Step 1: 【0357】 The server collects historical transaction information from each supply chain. As input, it accesses online store and physical store sales databases to obtain detailed data such as product names, sales quantities, and sales periods. This data is extracted through database queries and stored on the server. As output, the collected transaction information is organized into usable datasets. 【0358】 Step 2: 【0359】 The server trains a demand forecasting algorithm based on the collected transaction information. The transaction data generated in Step 1 is used as input. The server uses libraries such as Pandas and Scikit-learn to analyze this data, extract features, and build a model suitable for demand forecasting. The trained demand forecasting model is obtained as output, which is useful for future demand forecasting. 【0360】 Step 3: 【0361】 The server analyzes user emotional information using an emotion engine. Inputs include social media posts, customer reviews, and call center inquiry logs. The server utilizes natural language processing techniques to score emotions as positive, negative, or neutral. TensorFlow and NLTK are used for this analysis. The output generates data indicating the user's emotional tendencies. 【0362】 Step 4: 【0363】 The server integrates the analyzed sentiment information into the demand forecasting model. The demand forecasting model obtained in step 2 and the sentiment data from step 3 are used as input. The server adjusts the model parameters to perform a more accurate demand forecast that reflects the sentiment data. The output is a demand forecast result that takes sentiment information into account. 【0364】 Step 5: 【0365】 The server optimizes product allocation and manages assets based on demand forecast results. The demand forecast results obtained in step 4 are used as input. The server calculates inventory reallocation and issues instructions to maintain optimal inventory levels at each sales point. The output is optimized product allocation, streamlining inventory management. 【0366】 Step 6: 【0367】 The user receives forecast results and sales strategy feedback from the server. The input consists of forecast data and analysis results generated by the server. The user uses this information to adjust sales activities and campaign plans. The output is that the user's sales strategies are aligned with market demand, maximizing sales opportunities. 【0368】 (Application Example 2) 【0369】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal." 【0370】 Modern inventory management systems generally forecast demand and manage inventory based on historical sales data, but they fail to take into account customer sentiment and the elusive trends of the market, making it difficult to respond immediately to fluctuations in demand. This increases the risk of oversupply or undersupply, hindering efficient inventory management. Furthermore, the lack of means to predict the effectiveness of sales strategies means that promotions and campaigns are not being adequately optimized. 【0371】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0372】 In this invention, the server includes means for collecting historical sales data from each supply route, means for training a demand forecasting structure based on the collected sales data, and means for analyzing user sentiment data and integrating that sentiment data into the demand forecasting structure to improve the accuracy of demand. This enables advanced inventory management that incorporates customer sentiment and market trends. Furthermore, it enables immediate response to demand fluctuations through real-time monitoring of sales data and adjustment of supply allocation. 【0373】 "Supply route" refers to the concept of the path by which goods or services are delivered from the manufacturer or supplier to the consumer. 【0374】 "Sales data" refers to information that shows how much of a product or service was sold within a specific period, and typically includes quantity, price, and purchase date. 【0375】 A "demand forecast structure" refers to a statistical or computational model used to predict future demand levels based on historical data and market information. 【0376】 "Sentimental data" refers to information that reflects consumers' emotions and opinions, and is typically collected from sources such as social media, reviews, and survey results. 【0377】 "Inventory management" refers to the activities undertaken by companies and organizations to efficiently manage their inventory of goods and materials and to optimize the balance between supply and demand. 【0378】 A "sales strategy" refers to a plan or policy for effectively selling a product or service based on market and customer needs. 【0379】 This invention is an inventory management system that integrates sentiment data to improve demand forecasting. The system is implemented using a server, user terminals, and market information as a data source. 【0380】 The server collects historical sales data from each supply chain and uses this data to build a demand forecasting structure. The collected data undergoes a data cleaning process to prepare it for model training. During this process, data processing is performed using libraries such as Python's pandas and numpy. 【0381】 Next, natural language processing is performed to analyze user sentiment data. Sentiment data is obtained from social media posts and customer reviews, and positive / negative sentiment tendencies are evaluated using NLTK and TextBlob. This sentiment information is integrated as a feed into the demand forecasting structure, contributing to improving the accuracy of the model. 【0382】 The terminal receives recommended inventory allocations based on these analysis results, enabling real-time supply adjustments. It integrates with cloud computing services (e.g., AWS and Google Cloud) to perform dynamic data processing. 【0383】 As a concrete example, the system detects when a particular fashion brand gains attention on social media and predicts a surge in demand for that product category. If it determines there is a risk of inventory shortages, it immediately adjusts the supply allocation to increase the stock of the relevant product. 【0384】 The generative AI model can analyze sentiment data using the following prompt statements. 【0385】 "Collect recent tweets related to a specific product and analyze their sentiment scores." 【0386】 In this way, the server enables advanced inventory management to respond quickly to fluctuations in demand. 【0387】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0388】 Step 1: 【0389】 The server collects historical sales data from each supply route. Inputs are database and sensor data from the supply route, and output is the collected raw data. Sales data is extracted from the database using SQL queries and stored in CSV or JSON format. 【0390】 Step 2: 【0391】 The server cleans the collected sales data and prepares it in a format suitable for training the demand forecasting model. The input is the raw data obtained in step 1, and the output is the prepared dataset. Missing value handling and outlier detection are performed using the Python pandas library. 【0392】 Step 3: 【0393】 The server collects user sentiment data from social media and customer reviews, and uses natural language processing to evaluate sentiment tendencies. The input is text from social media posts and reviews, and the output is a sentiment score. NLTK and TextBlob are used to analyze the text and calculate positive and negative scores. 【0394】 Step 4: 【0395】 The server integrates sentiment data into a demand forecasting model to improve its accuracy. The input is a prepared dataset and sentiment scores, and the output is an enhanced demand forecasting model. The machine learning library scikit-learn is used to retrain the model. 【0396】 Step 5: 【0397】 The terminal receives recommended inventory allocations based on an enhanced demand forecasting model. The input is forecast data from the enhanced demand forecasting model, and the output is the recommended inventory allocation. It communicates with the cloud system via a real-time API to retrieve the recommended allocation. 【0398】 Step 6: 【0399】 The user reviews the recommended inventory allocation and supply adjustment notifications on the terminal and makes adjustments as needed. The input is the recommended allocation from step 5, and the output is the actual inventory adjustment result. The user reviews the information provided through the terminal's UI and makes adjustments manually. 【0400】 The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0401】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0402】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214. 【0403】 [Third Embodiment] 【0404】 Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment. 【0405】 As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server. 【0406】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0407】 The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52. 【0408】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0409】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0410】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0411】 Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0412】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0413】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0414】 In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0415】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal". 【0416】 This invention is a system for streamlining inventory management, aiming to automate demand forecasting and inventory allocation. The following describes embodiments for carrying out the invention based on the claims. 【0417】 This system primarily consists of a process where a server collects and analyzes sales information and then uses that information to forecast demand. Specifically, the server collects historical sales information from each sales channel. The collected information includes sales quantity, sales date, and number of units sold for each product. This allows for an understanding of the demand patterns for each sales channel. 【0418】 Next, the server analyzes the collected sales information to identify sales trends. For example, if a particular product is affected by seasonality or if sales are concentrated during a specific period, these characteristics are taken into account. This allows for the construction of a demand forecasting model. 【0419】 The server then uses a demand forecasting model to predict future demand. Based on the predicted demand, the server optimizes inventory allocation to each sales channel. This prevents excess inventory and shortages, enabling efficient inventory management. 【0420】 Furthermore, the server monitors sales in real time and quickly adjusts inventory allocation if a discrepancy is detected between forecasts and actual sales. For example, if demand suddenly surges due to a promotional event, the server immediately adjusts inventory to avoid shortages. In this way, the system of the present invention enables optimal inventory management for each sales channel. 【0421】 As a concrete example, in large retail stores, this system functions effectively to respond to regular promotions and seasonal fluctuations in demand. Based on historical data, the server predicts that certain products will sell well during the Christmas season and allocates inventory accordingly. As a result, the burden on the user (the manager) to manually adjust inventory is reduced, allowing them to carry out their work with greater efficiency. In this way, the system of the present invention achieves inventory management that is both efficient and accurate. 【0422】 The following describes the processing flow. 【0423】 Step 1: 【0424】 The server works in conjunction with the sales management system to periodically collect historical sales information from each sales channel. This sales information includes data such as product ID, sales date, and sales quantity. 【0425】 Step 2: 【0426】 The server stores the collected sales information in a database and performs initial data preprocessing. Specifically, it performs tasks such as imputing missing data and detecting and correcting outliers. This process creates a dataset suitable for analysis. 【0427】 Step 3: 【0428】 The server extracts features necessary for demand forecasting from sales information. These features include elements that are thought to influence demand, such as the day of the week, month, date of a specific event, and seasonal factors. 【0429】 Step 4: 【0430】 The server uses machine learning algorithms to train a demand forecasting model. Based on past sales data, patterns are input into the forecasting model to analyze future sales trends. At this stage, cross-validation is also performed to improve the accuracy of the model. 【0431】 Step 5: 【0432】 The server uses a trained model to predict future demand. It forecasts sales volume for each sales channel in the following week or month and calculates the required inventory based on that. 【0433】 Step 6: 【0434】 The server calculates inventory allocation based on the forecast results and distributes the optimal amount of inventory to each sales channel. This includes considering factors such as inventory costs and lead times. 【0435】 Step 7: 【0436】 The server monitors sales in real time. Based on the collected real-time sales data, it adjusts inventory allocation plans if there are discrepancies with forecasts. For example, it prepares for unexpected large-scale purchase events. 【0437】 Step 8: 【0438】 Users can review inventory allocation information provided by the server and request corrections from the supply chain as needed. They can also refer to reports generated by the server to improve their inventory policies. 【0439】 (Example 1) 【0440】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0441】 In inventory management, a key challenge is efficiently optimizing demand forecasting and inventory allocation using historical sales data. Currently, inventory adjustments are often done manually, leading to human error and inefficiencies. Furthermore, it is difficult to respond quickly to real-time demand fluctuations. 【0442】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0443】 In this invention, the server includes means for collecting historical sales data from each distribution channel, means for analyzing the collected sales data to identify sales trends, and means for constructing a demand forecasting model based on the identified sales trends. This enables accurate understanding of demand trends in each distribution channel, flexible response to differences between forecasts and actual distribution, and optimization of inventory allocation. 【0444】 "Distribution channels" refer to the entire sales channel involved in the process from when a product is produced until it reaches the consumer. 【0445】 "Sales data" refers to a collection of data that includes the quantity sold, unit price, sales date, and other related information for a product over a certain period. 【0446】 "Sales trends" refer to information that shows the tendencies and patterns related to product sales, based on analysis of past sales data. 【0447】 A "demand forecasting model" is a mathematical model constructed to predict future demand for a product based on past sales trends and external influencing factors. 【0448】 "Inventory allocation" is the process of efficiently allocating goods to various distribution channels and storage locations according to demand. 【0449】 "Optimization" is a methodology for making the most of resources under certain conditions to obtain the best possible results. 【0450】 "Real-time" is a concept that indicates that processing takes place almost simultaneously with real-world time. 【0451】 "Difference" refers to the difference between the predicted value and the actual value. 【0452】 This invention is a system that streamlines inventory management and optimizes inventory through demand forecasting. The following hardware and software are used to implement the system. 【0453】 The server plays a central role in automatically collecting sales data from each distribution channel and analyzing that data. Specifically, the server stores the data using a database management system, and uses programming languages ​​such as Python and R, along with their libraries (e.g., Pandas, NumPy), for data analysis. It also uses TensorFlow or PyTorch as a machine learning framework to build and train demand forecasting models. 【0454】 Users perform their tasks based on demand forecasts and inventory allocation plans provided by the server. By utilizing a generative AI model, users receive program advice to support their inventory management decisions. An example of a prompt to the AI ​​is: "Based on sales data for a specific product over the past three years, how can I forecast demand for the next season?" 【0455】 As a concrete example, in a retail setting, a server analyzes historical data prior to the Christmas season to predict increased demand for specific products. As a result, appropriate inventory allocation is made in advance, reducing the risk of stockouts and excess inventory. Inventory managers, who are the users of the system, can reduce the need for manual adjustments and improve operational efficiency. 【0456】 Thus, the system of the present invention plays a role in solving challenges in inventory management and supporting smooth business operations by accurately grasping sales trends and responding quickly to demand. 【0457】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0458】 Step 1: 【0459】 The server collects sales data from each distribution channel. The input is raw sales data obtained from the database of each distribution channel, which includes information such as product name, sales quantity, and sales date. This data is stored in the server's database management system and used as the basis for future analysis. 【0460】 Step 2: 【0461】 The server preprocesses the collected sales data. The input is the sales data collected in step 1. Specifically, the server performs data cleaning, including imputing missing values ​​and removing duplicate data. It uses the Python Pandas library to format the data, making it suitable for analysis and model building. The output is clean and formatted sales data. 【0462】 Step 3: 【0463】 The server analyzes pre-processed data to identify sales trends. The input is formatted sales data, and the server uses time series analysis to identify best-selling products and seasonal trends. It employs ARIMA models and other statistical methods for analysis. The output is data related to the identified sales trends. 【0464】 Step 4: 【0465】 The server builds a demand forecasting model based on sales trends. The input is the sales trend data obtained in step 3. The model is trained and learned using the machine learning framework TensorFlow. The server evaluates the model's performance and sets appropriate model parameters. The output is the constructed demand forecasting model. 【0466】 Step 5: 【0467】 The server uses a demand forecasting model to predict future demand. The input is new market data and trend information, and the model is executed to generate forecast data. The AI-generated forecast results are output, generating data indicating the required inventory levels for each distribution channel. 【0468】 Step 6: 【0469】 The server uses the forecast results to optimize inventory. The input is the forecast demand data obtained in step 5. The server uses optimization methods such as linear programming to calculate inventory allocation to each distribution channel. The output is the optimized inventory allocation plan. 【0470】 Step 7: 【0471】 The server monitors distribution information in real time and checks for discrepancies between forecasts and actual sales. The input is real-time sales data, monitored using a system like Kafka. If the server detects a discrepancy, it immediately readjusts inventory allocation to prevent shortages or surpluses. The output is the updated inventory allocation plan. 【0472】 (Application Example 1) 【0473】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0474】 In today's logistics and sales industries, streamlining inventory management and maximizing sales opportunities are major challenges. In particular, responding quickly to real-time demand fluctuations and allocating inventory appropriately is difficult. Furthermore, there is a need for systems that allow sales managers to accurately understand inventory levels and take swift action. 【0475】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0476】 In this invention, the server includes means for collecting historical sales information from each sales channel, means for training a demand forecasting model based on the collected sales information, and means for generating inventory management warnings using a mobile information processing device and notifying sales managers. This enables sales managers to grasp the inventory status in real time and adjust inventory allocation quickly and accurately. 【0477】 "Sales channels" refer to the entire distribution and sales route from the time a product reaches the consumer. 【0478】 A "demand forecasting model" is a model that uses statistical or machine learning methods to predict future sales volume and timing based on past sales data. 【0479】 "Inventory allocation" is the process of efficiently distributing inventory across multiple sales locations and warehouses. 【0480】 A "mobile information processing device" refers to a portable computing device, specifically a smartphone or tablet, that has the function of processing and displaying information. 【0481】 "Sales information" is a general term for various sales-related data, including sales quantity, sales date, and number of units sold for each product. 【0482】 "Features" are numerical data that represent the characteristics of the subject being analyzed in data analysis and machine learning, and are used as input for models. 【0483】 "Cleaning" refers to the process of removing and correcting noise and missing data, and preparing it in a format suitable for analysis. 【0484】 A "warning" refers to a notification or message that alerts the user when certain conditions occur. 【0485】 In implementing the present invention, the system is configured as follows: The server collects historical sales information from each sales channel and trains a demand forecasting model. Specifically, the server retrieves sales data from a database and performs preprocessing using a programming language such as Python. In this process, data cleaning is performed to remove noise and missing data and prepare the data for analysis. 【0486】 Next, the server uses machine learning libraries such as TensorFlow to build a demand forecasting model based on the cleaned data. This model accurately predicts future demand based on historical data and calculates the optimal inventory allocation. 【0487】 Users can use mobile information processing devices such as smartphones and tablets to check inventory status in real time. Here, a mobile application is developed using a cross-platform framework such as React Native. This application displays inventory allocation data and warnings sent from the server, providing sales managers with immediate action plans. 【0488】 As a concrete example, in a logistics center, if inventory of a specific product that sees increased demand during a certain season is likely to run low, a warning will be displayed on a mobile device. This warning allows sales managers to immediately arrange for additional stock and prevent shortages. 【0489】 To further utilize this system, a generative AI model can be used to generate prompts like the following, improving the accuracy of demand forecasting: "Based on sales data for a specific product during the Christmas season over the past three years, please tell me how to forecast next year's demand and optimize inventory allocation." 【0490】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0491】 Step 1: 【0492】 The server collects historical sales information from each sales channel. The input is a sales information database, and the output is the collected sales data. The data is retrieved via an API and includes sales quantity, sales date, number of units sold, etc. This prepares the system to understand the demand patterns of each sales channel. 【0493】 Step 2: 【0494】 The server cleans the collected sales information. The input is the data collected in step 1, and the output is clean data with noise and missing data removed. This process uses Python, and a data cleaning script is applied to prepare the data for analysis. 【0495】 Step 3: 【0496】 The server trains a demand forecasting model based on the cleaned data. The input is the cleaned data from step 2, and the output is the trained demand forecasting model. Here, TensorFlow is used to build a model that predicts future demand from historical data. 【0497】 Step 4: 【0498】 The server uses a trained model to predict future demand. The input is the trained model from step 3 and the latest sales data, and the output is predicted demand data. Based on this, highly accurate demand forecasts are made. 【0499】 Step 5: 【0500】 The server calculates inventory allocation based on predicted demand. The input is the demand forecast data from step 4, and the output is the optimized inventory allocation data. The inventory allocation algorithm is executed to determine the inventory allocation to each sales location. 【0501】 Step 6: 【0502】 The terminal displays inventory status and warnings on a mobile information processing device. Input is inventory allocation data from the server, and output is the screen display on the terminal. React Native is used to provide real-time inventory information visually to the user. 【0503】 Step 7: 【0504】 Users check inventory status via their devices and take action as needed. Input is the information displayed on the device screen, while output is the user's decisions and actions. Mobile applications allow for immediate execution of sales plans and replenishment orders. 【0505】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0506】 This invention provides a system that further optimizes demand forecasting and inventory allocation by combining an emotion engine that recognizes user emotions with an inventory management system. In this invention, a program running on a server analyzes user emotion information and improves the accuracy of the demand forecasting model based on that analysis. 【0507】 Specifically, the server first builds a demand forecasting model based on sales information collected from each sales channel. In addition, the emotion engine analyzes users' emotional states in real time, understanding the overall emotional trends of consumers from sources such as social media, customer reviews, and call center inquiries. This emotional data is input into the demand forecasting model, influencing future demand forecasts. 【0508】 Furthermore, the server can use user sentiment data analyzed by the sentiment engine to predict the effectiveness of sales campaigns and promotions. This allows for the creation of inventory allocation plans that anticipate user responses in advance, enabling inventory management with a buffer to cope with sudden fluctuations in demand. 【0509】 As a concrete example, if the server detects an increase in customer reviews for a particular product using its sentiment engine, it reflects the potential for increased demand for that product in its demand forecasting model and secures additional inventory in advance. This coordination between forecasting and inventory allocation allows retailers, as users, to always provide customers with the products they need. 【0510】 Furthermore, users can provide feedback on sales strategies through the emotion engine and interface. This allows for a direct understanding of how to meet consumer needs and strengthens the overall inventory management strategy. In this way, the present invention achieves a higher level of inventory optimization by combining user emotion analysis with traditional inventory management. 【0511】 The following describes the processing flow. 【0512】 Step 1: 【0513】 The server collects historical sales information from each sales channel and stores it in a database. The collected data includes sales volume, sales period, customer attributes, and more. 【0514】 Step 2: 【0515】 The server uses the collected sales information to create a demand forecasting model and uses machine learning algorithms to improve the accuracy of the forecast. 【0516】 Step 3: 【0517】 The server uses an emotion engine to analyze user emotions from various sources, such as social media and review sites. This allows for an understanding of consumers' emotional state towards a product. 【0518】 Step 4: 【0519】 The server integrates sentiment data into the demand forecasting model and applies sentiment-based adjustments to further improve the accuracy of demand forecasts. The model reflects increases in positive sentiment towards the product in the forecasted demand. 【0520】 Step 5: 【0521】 The server calculates the optimal inventory allocation based on future demand forecasts and instructs each sales channel to apply it. Inventory allocation follows the results calculated from predicted demand and market sentiment trends. 【0522】 Step 6: 【0523】 The server monitors sales in real time and dynamically readjusts inventory allocation and distribution plans if a discrepancy is found between forecasts and actual sales. Sentiment data fluctuations are also re-evaluated during this process. 【0524】 Step 7: 【0525】 Users review reports generated by the server and incorporate them into sales strategies and inventory management policies. The results of sentiment analysis performed by the server are also used in strategic decision-making. 【0526】 Step 8: 【0527】 The device receives user feedback as needed and feeds that feedback back into both the emotion engine and the demand forecasting model. This improves the overall adaptability of the system. 【0528】 (Example 2) 【0529】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0530】 Traditional inventory management systems relied on sales data for demand forecasting, but they failed to adequately consider consumer sentiment and market trends, making it difficult to respond flexibly to fluctuations in demand. Furthermore, discrepancies between forecasting models and actual sales data could occur, hindering the optimization of inventory allocation. Therefore, there is a need for more accurate and flexible inventory management. 【0531】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0532】 In this invention, the server includes means for collecting past transaction information from each supply route, means for training a demand forecasting algorithm based on the collected transaction information, and means for analyzing user sentiment information and reflecting the analysis results in the demand forecasting algorithm. By incorporating the emotional state of consumers into the demand forecast, it becomes possible to achieve more accurate demand forecasting and optimization of inventory allocation. 【0533】 "Supply chain" refers to the entire path a product takes from the manufacturer or distribution center to the consumer, and includes wholesalers, retailers, and online sales platforms. 【0534】 "Transaction information" refers to detailed data about the sale of a product, including information such as sales quantity, sales price, transaction date and time, and transaction region. 【0535】 A "demand forecasting algorithm" refers to a computational method or model used to predict future demand for a product based on collected data, enabling companies to rationally plan the necessary inventory and production volumes. 【0536】 "Emotional information" refers to data that indicates consumers' emotional states and emotional trends in the market, and is obtained from sources such as social media posts, customer reviews, and inquiries. 【0537】 "Learning" refers to the process by which an algorithm finds patterns and rules from the provided data and automatically updates the model to make highly accurate predictions. 【0538】 "Product allocation" refers to the process of appropriately allocating and supplying products to each sales location based on demand forecasts, and is an important activity for achieving efficient inventory management. 【0539】 "Assets" refer to all of the goods, property, and intellectual property owned by a company, and the management and optimization of these improve the operational efficiency of the company. 【0540】 "Discrepancy" refers to the difference between predicted demand and actual observed sales, and resolving this discrepancy leads to improved accuracy in inventory management. 【0541】 The embodiments for carrying out the invention are shown below. 【0542】 In this invention, the server integrates an inventory management system with an emotion engine that recognizes user emotions to achieve more accurate demand forecasting and optimized inventory allocation. Specifically, the server collects transaction information from each supply route and uses this information to train a demand forecasting algorithm. For training, it uses Python libraries for data analysis such as Pandas and Scikit-learn. Furthermore, it utilizes the emotion engine to analyze consumer emotion information in real time from various sources such as social media, customer reviews, and call center inquiries. For this analysis, it uses natural language processing libraries such as TensorFlow and NLTK. 【0543】 After transaction and sentiment data are analyzed, the server incorporates the sentiment data into a demand forecasting algorithm to predict future demand. Based on this forecast, the server adjusts product allocation to support efficient inventory management. The server also has the ability to constantly monitor the forecasting model and actual transaction data, and adjust product allocation as needed. 【0544】 For example, if consumer sentiment information about a particular cosmetic product rapidly gains positive reviews on social media, the server can use that data to predict the increase in demand and meet consumer needs by securing additional inventory in advance. In this way, retailers, as users, can provide consumers with the necessary products in a timely manner without missing sales opportunities. 【0545】 An example of a prompt to input into the generating AI model might be, "How can we build a demand forecasting model to optimize inventory allocation for each store?" This prompt allows for the development of new algorithms to improve demand forecasting accuracy. 【0546】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0547】 Step 1: 【0548】 The server collects historical transaction information from each supply chain. As input, it accesses online store and physical store sales databases to obtain detailed data such as product names, sales quantities, and sales periods. This data is extracted through database queries and stored on the server. As output, the collected transaction information is organized into usable datasets. 【0549】 Step 2: 【0550】 The server trains a demand forecasting algorithm based on the collected transaction information. The transaction data generated in Step 1 is used as input. The server uses libraries such as Pandas and Scikit-learn to analyze this data, extract features, and build a model suitable for demand forecasting. The trained demand forecasting model is obtained as output, which is useful for future demand forecasting. 【0551】 Step 3: 【0552】 The server analyzes user emotional information using an emotion engine. Inputs include social media posts, customer reviews, and call center inquiry logs. The server utilizes natural language processing techniques to score emotions as positive, negative, or neutral. TensorFlow and NLTK are used for this analysis. The output generates data indicating the user's emotional tendencies. 【0553】 Step 4: 【0554】 The server integrates the analyzed sentiment information into the demand forecasting model. The demand forecasting model obtained in step 2 and the sentiment data from step 3 are used as input. The server adjusts the model parameters to perform a more accurate demand forecast that reflects the sentiment data. The output is a demand forecast result that takes sentiment information into account. 【0555】 Step 5: 【0556】 The server optimizes product allocation and manages assets based on demand forecast results. The demand forecast results obtained in step 4 are used as input. The server calculates inventory reallocation and issues instructions to maintain optimal inventory levels at each sales point. The output is optimized product allocation, streamlining inventory management. 【0557】 Step 6: 【0558】 The user receives forecast results and sales strategy feedback from the server. The input consists of forecast data and analysis results generated by the server. The user uses this information to adjust sales activities and campaign plans. The output is that the user's sales strategies are aligned with market demand, maximizing sales opportunities. 【0559】 (Application Example 2) 【0560】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal." 【0561】 Modern inventory management systems generally forecast demand and manage inventory based on historical sales data, but they fail to take into account customer sentiment and the elusive trends of the market, making it difficult to respond immediately to fluctuations in demand. This increases the risk of oversupply or undersupply, hindering efficient inventory management. Furthermore, the lack of means to predict the effectiveness of sales strategies means that promotions and campaigns are not being adequately optimized. 【0562】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0563】 In this invention, the server includes means for collecting historical sales data from each supply route, means for training a demand forecasting structure based on the collected sales data, and means for analyzing user sentiment data and integrating that sentiment data into the demand forecasting structure to improve the accuracy of demand. This enables advanced inventory management that incorporates customer sentiment and market trends. Furthermore, it enables immediate response to demand fluctuations through real-time monitoring of sales data and adjustment of supply allocation. 【0564】 "Supply route" refers to the concept of the path by which goods or services are delivered from the manufacturer or supplier to the consumer. 【0565】 "Sales data" refers to information that shows how much of a product or service was sold within a specific period, and typically includes quantity, price, and purchase date. 【0566】 A "demand forecast structure" refers to a statistical or computational model used to predict future demand levels based on historical data and market information. 【0567】 "Sentimental data" refers to information that reflects consumers' emotions and opinions, and is typically collected from sources such as social media, reviews, and survey results. 【0568】 "Inventory management" refers to the activities undertaken by companies and organizations to efficiently manage their inventory of goods and materials and to optimize the balance between supply and demand. 【0569】 A "sales strategy" refers to a plan or policy for effectively selling a product or service based on market and customer needs. 【0570】 This invention is an inventory management system that integrates sentiment data to improve demand forecasting. The system is implemented using a server, user terminals, and market information as a data source. 【0571】 The server collects historical sales data from each supply chain and uses this data to build a demand forecasting structure. The collected data undergoes a data cleaning process to prepare it for model training. During this process, data processing is performed using libraries such as Python's pandas and numpy. 【0572】 Next, natural language processing is performed to analyze user sentiment data. Sentiment data is obtained from social media posts and customer reviews, and positive / negative sentiment tendencies are evaluated using NLTK and TextBlob. This sentiment information is integrated as a feed into the demand forecasting structure, contributing to improving the accuracy of the model. 【0573】 The terminal receives recommended inventory allocations based on these analysis results, enabling real-time supply adjustments. It integrates with cloud computing services (e.g., AWS and Google Cloud) to perform dynamic data processing. 【0574】 As a concrete example, the system detects when a particular fashion brand gains attention on social media and predicts a surge in demand for that product category. If it determines there is a risk of inventory shortages, it immediately adjusts the supply allocation to increase the stock of the relevant product. 【0575】 The generative AI model can analyze sentiment data using the following prompt statements. 【0576】 "Collect recent tweets related to a specific product and analyze their sentiment scores." 【0577】 In this way, the server enables advanced inventory management to respond quickly to fluctuations in demand. 【0578】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0579】 Step 1: 【0580】 The server collects historical sales data from each supply route. Inputs are database and sensor data from the supply route, and output is the collected raw data. Sales data is extracted from the database using SQL queries and stored in CSV or JSON format. 【0581】 Step 2: 【0582】 The server cleans the collected sales data and prepares it in a format suitable for training the demand forecasting model. The input is the raw data obtained in step 1, and the output is the prepared dataset. Missing value handling and outlier detection are performed using the Python pandas library. 【0583】 Step 3: 【0584】 The server collects user sentiment data from social media and customer reviews, and uses natural language processing to evaluate sentiment tendencies. The input is text from social media posts and reviews, and the output is a sentiment score. NLTK and TextBlob are used to analyze the text and calculate positive and negative scores. 【0585】 Step 4: 【0586】 The server integrates sentiment data into a demand forecasting model to improve its accuracy. The input is a prepared dataset and sentiment scores, and the output is an enhanced demand forecasting model. The machine learning library scikit-learn is used to retrain the model. 【0587】 Step 5: 【0588】 The terminal receives recommended inventory allocations based on an enhanced demand forecasting model. The input is forecast data from the enhanced demand forecasting model, and the output is the recommended inventory allocation. It communicates with the cloud system via a real-time API to retrieve the recommended allocation. 【0589】 Step 6: 【0590】 The user reviews the recommended inventory allocation and supply adjustment notifications on the terminal and makes adjustments as needed. The input is the recommended allocation from step 5, and the output is the actual inventory adjustment result. The user reviews the information provided through the terminal's UI and makes adjustments manually. 【0591】 The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0592】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0593】 In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314. 【0594】 [Fourth Embodiment] 【0595】 Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment. 【0596】 As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server. 【0597】 The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network). 【0598】 The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52. 【0599】 The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46. 【0600】 Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision). 【0601】 Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner. 【0602】 The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes. 【0603】 Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56. 【0604】 The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30. 【0605】 The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. 【0606】 In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48. 【0607】 Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0608】 This invention is a system for streamlining inventory management, aiming to automate demand forecasting and inventory allocation. The following describes embodiments for carrying out the invention based on the claims. 【0609】 This system primarily consists of a process where a server collects and analyzes sales information and then uses that information to forecast demand. Specifically, the server collects historical sales information from each sales channel. The collected information includes sales quantity, sales date, and number of units sold for each product. This allows for an understanding of the demand patterns for each sales channel. 【0610】 Next, the server analyzes the collected sales information to identify sales trends. For example, if a particular product is affected by seasonality or if sales are concentrated during a specific period, these characteristics are taken into account. This allows for the construction of a demand forecasting model. 【0611】 The server then uses a demand forecasting model to predict future demand. Based on the predicted demand, the server optimizes inventory allocation to each sales channel. This prevents excess inventory and shortages, enabling efficient inventory management. 【0612】 Furthermore, the server monitors sales in real time and quickly adjusts inventory allocation if a discrepancy is detected between forecasts and actual sales. For example, if demand suddenly surges due to a promotional event, the server immediately adjusts inventory to avoid shortages. In this way, the system of the present invention enables optimal inventory management for each sales channel. 【0613】 As a concrete example, in large retail stores, this system functions effectively to respond to regular promotions and seasonal fluctuations in demand. Based on historical data, the server predicts that certain products will sell well during the Christmas season and allocates inventory accordingly. As a result, the burden on the user (the manager) to manually adjust inventory is reduced, allowing them to carry out their work with greater efficiency. In this way, the system of the present invention achieves inventory management that is both efficient and accurate. 【0614】 The following describes the processing flow. 【0615】 Step 1: 【0616】 The server works in conjunction with the sales management system to periodically collect historical sales information from each sales channel. This sales information includes data such as product ID, sales date, and sales quantity. 【0617】 Step 2: 【0618】 The server stores the collected sales information in a database and performs initial data preprocessing. Specifically, it performs tasks such as imputing missing data and detecting and correcting outliers. This process creates a dataset suitable for analysis. 【0619】 Step 3: 【0620】 The server extracts features necessary for demand forecasting from sales information. These features include elements that are thought to influence demand, such as the day of the week, month, date of a specific event, and seasonal factors. 【0621】 Step 4: 【0622】 The server uses machine learning algorithms to train a demand forecasting model. Based on past sales data, patterns are input into the forecasting model to analyze future sales trends. At this stage, cross-validation is also performed to improve the accuracy of the model. 【0623】 Step 5: 【0624】 The server uses a trained model to predict future demand. It forecasts sales volume for each sales channel in the following week or month and calculates the required inventory based on that. 【0625】 Step 6: 【0626】 The server calculates inventory allocation based on the forecast results and distributes the optimal amount of inventory to each sales channel. This includes considering factors such as inventory costs and lead times. 【0627】 Step 7: 【0628】 The server monitors sales in real time. Based on the collected real-time sales data, it adjusts inventory allocation plans if there are discrepancies with forecasts. For example, it prepares for unexpected large-scale purchase events. 【0629】 Step 8: 【0630】 Users can review inventory allocation information provided by the server and request corrections from the supply chain as needed. They can also refer to reports generated by the server to improve their inventory policies. 【0631】 (Example 1) 【0632】 Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0633】 In inventory management, a key challenge is efficiently optimizing demand forecasting and inventory allocation using historical sales data. Currently, inventory adjustments are often done manually, leading to human error and inefficiencies. Furthermore, it is difficult to respond quickly to real-time demand fluctuations. 【0634】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means. 【0635】 In this invention, the server includes means for collecting historical sales data from each distribution channel, means for analyzing the collected sales data to identify sales trends, and means for constructing a demand forecasting model based on the identified sales trends. This enables accurate understanding of demand trends in each distribution channel, flexible response to differences between forecasts and actual distribution, and optimization of inventory allocation. 【0636】 "Distribution channels" refer to the entire sales channel involved in the process from when a product is produced until it reaches the consumer. 【0637】 "Sales data" refers to a collection of data that includes the quantity sold, unit price, sales date, and other related information for a product over a certain period. 【0638】 "Sales trends" refer to information that shows the tendencies and patterns related to product sales, based on analysis of past sales data. 【0639】 A "demand forecasting model" is a mathematical model constructed to predict future demand for a product based on past sales trends and external influencing factors. 【0640】 "Inventory allocation" is the process of efficiently allocating goods to various distribution channels and storage locations according to demand. 【0641】 "Optimization" is a methodology for making the most of resources under certain conditions to obtain the best possible results. 【0642】 "Real-time" is a concept that indicates that processing takes place almost simultaneously with real-world time. 【0643】 "Difference" refers to the difference between the predicted value and the actual value. 【0644】 This invention is a system that streamlines inventory management and optimizes inventory through demand forecasting. The following hardware and software are used to implement the system. 【0645】 The server plays a central role in automatically collecting sales data from each distribution channel and analyzing that data. Specifically, the server stores the data using a database management system, and uses programming languages ​​such as Python and R, along with their libraries (e.g., Pandas, NumPy), for data analysis. It also uses TensorFlow or PyTorch as a machine learning framework to build and train demand forecasting models. 【0646】 Users perform their tasks based on demand forecasts and inventory allocation plans provided by the server. By utilizing a generative AI model, users receive program advice to support their inventory management decisions. An example of a prompt to the AI ​​is: "Based on sales data for a specific product over the past three years, how can I forecast demand for the next season?" 【0647】 As a concrete example, in a retail setting, a server analyzes historical data prior to the Christmas season to predict increased demand for specific products. As a result, appropriate inventory allocation is made in advance, reducing the risk of stockouts and excess inventory. Inventory managers, who are the users of the system, can reduce the need for manual adjustments and improve operational efficiency. 【0648】 Thus, the system of the present invention plays a role in solving challenges in inventory management and supporting smooth business operations by accurately grasping sales trends and responding quickly to demand. 【0649】 The flow of the specific processing in Example 1 will be explained using Figure 11. 【0650】 Step 1: 【0651】 The server collects sales data from each distribution channel. The input is raw sales data obtained from the database of each distribution channel, which includes information such as product name, sales quantity, and sales date. This data is stored in the server's database management system and used as the basis for future analysis. 【0652】 Step 2: 【0653】 The server preprocesses the collected sales data. The input is the sales data collected in step 1. Specifically, the server performs data cleaning, including imputing missing values ​​and removing duplicate data. It uses the Python Pandas library to format the data, making it suitable for analysis and model building. The output is clean and formatted sales data. 【0654】 Step 3: 【0655】 The server analyzes pre-processed data to identify sales trends. The input is formatted sales data, and the server uses time series analysis to identify best-selling products and seasonal trends. It employs ARIMA models and other statistical methods for analysis. The output is data related to the identified sales trends. 【0656】 Step 4: 【0657】 The server builds a demand forecasting model based on sales trends. The input is the sales trend data obtained in step 3. The model is trained and learned using the machine learning framework TensorFlow. The server evaluates the model's performance and sets appropriate model parameters. The output is the constructed demand forecasting model. 【0658】 Step 5: 【0659】 The server uses a demand forecasting model to predict future demand. The input is new market data and trend information, and the model is executed to generate forecast data. The AI-generated forecast results are output, generating data indicating the required inventory levels for each distribution channel. 【0660】 Step 6: 【0661】 The server uses the forecast results to optimize inventory. The input is the forecast demand data obtained in step 5. The server uses optimization methods such as linear programming to calculate inventory allocation to each distribution channel. The output is the optimized inventory allocation plan. 【0662】 Step 7: 【0663】 The server monitors distribution information in real time and checks for discrepancies between forecasts and actual sales. The input is real-time sales data, monitored using a system like Kafka. If the server detects a discrepancy, it immediately readjusts inventory allocation to prevent shortages or surpluses. The output is the updated inventory allocation plan. 【0664】 (Application Example 1) 【0665】 Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0666】 In today's logistics and sales industries, streamlining inventory management and maximizing sales opportunities are major challenges. In particular, responding quickly to real-time demand fluctuations and allocating inventory appropriately is difficult. Furthermore, there is a need for systems that allow sales managers to accurately understand inventory levels and take swift action. 【0667】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. 【0668】 In this invention, the server includes means for collecting historical sales information from each sales channel, means for training a demand forecasting model based on the collected sales information, and means for generating inventory management warnings using a mobile information processing device and notifying sales managers. This enables sales managers to grasp the inventory status in real time and adjust inventory allocation quickly and accurately. 【0669】 "Sales channels" refer to the entire distribution and sales route from the time a product reaches the consumer. 【0670】 A "demand forecasting model" is a model that uses statistical or machine learning methods to predict future sales volume and timing based on past sales data. 【0671】 "Inventory allocation" is the process of efficiently distributing inventory across multiple sales locations and warehouses. 【0672】 A "mobile information processing device" refers to a portable computing device, specifically a smartphone or tablet, that has the function of processing and displaying information. 【0673】 "Sales information" is a general term for various sales-related data, including sales quantity, sales date, and number of units sold for each product. 【0674】 "Features" are numerical data that represent the characteristics of the subject being analyzed in data analysis and machine learning, and are used as input for models. 【0675】 "Cleaning" refers to the process of removing and correcting noise and missing data, and preparing it in a format suitable for analysis. 【0676】 A "warning" refers to a notification or message that alerts the user when certain conditions occur. 【0677】 In implementing the present invention, the system is configured as follows: The server collects historical sales information from each sales channel and trains a demand forecasting model. Specifically, the server retrieves sales data from a database and performs preprocessing using a programming language such as Python. In this process, data cleaning is performed to remove noise and missing data and prepare the data for analysis. 【0678】 Next, the server uses machine learning libraries such as TensorFlow to build a demand forecasting model based on the cleaned data. This model accurately predicts future demand based on historical data and calculates the optimal inventory allocation. 【0679】 Users can use mobile information processing devices such as smartphones and tablets to check inventory status in real time. Here, a mobile application is developed using a cross-platform framework such as React Native. This application displays inventory allocation data and warnings sent from the server, providing sales managers with immediate action plans. 【0680】 As a concrete example, in a logistics center, if inventory of a specific product that sees increased demand during a certain season is likely to run low, a warning will be displayed on a mobile device. This warning allows sales managers to immediately arrange for additional stock and prevent shortages. 【0681】 To further utilize this system, a generative AI model can be used to generate prompts like the following, improving the accuracy of demand forecasting: "Based on sales data for a specific product during the Christmas season over the past three years, please tell me how to forecast next year's demand and optimize inventory allocation." 【0682】 The flow of a specific process in Application Example 1 will be explained using Figure 12. 【0683】 Step 1: 【0684】 The server collects historical sales information from each sales channel. The input is a sales information database, and the output is the collected sales data. The data is retrieved via an API and includes sales quantity, sales date, number of units sold, etc. This prepares the system to understand the demand patterns of each sales channel. 【0685】 Step 2: 【0686】 The server cleans the collected sales information. The input is the data collected in step 1, and the output is clean data with noise and missing data removed. This process uses Python, and a data cleaning script is applied to prepare the data for analysis. 【0687】 Step 3: 【0688】 The server trains a demand forecasting model based on the cleaned data. The input is the cleaned data from step 2, and the output is the trained demand forecasting model. Here, TensorFlow is used to build a model that predicts future demand from historical data. 【0689】 Step 4: 【0690】 The server uses a trained model to predict future demand. The input is the trained model from step 3 and the latest sales data, and the output is predicted demand data. Based on this, highly accurate demand forecasts are made. 【0691】 Step 5: 【0692】 The server calculates inventory allocation based on predicted demand. The input is the demand forecast data from step 4, and the output is the optimized inventory allocation data. The inventory allocation algorithm is executed to determine the inventory allocation to each sales location. 【0693】 Step 6: 【0694】 The terminal displays inventory status and warnings on a mobile information processing device. Input is inventory allocation data from the server, and output is the screen display on the terminal. React Native is used to provide real-time inventory information visually to the user. 【0695】 Step 7: 【0696】 Users check inventory status via their devices and take action as needed. Input is the information displayed on the device screen, while output is the user's decisions and actions. Mobile applications allow for immediate execution of sales plans and replenishment orders. 【0697】 Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions. 【0698】 This invention provides a system that further optimizes demand forecasting and inventory allocation by combining an emotion engine that recognizes user emotions with an inventory management system. In this invention, a program running on a server analyzes user emotion information and improves the accuracy of the demand forecasting model based on that analysis. 【0699】 Specifically, the server first builds a demand forecasting model based on sales information collected from each sales channel. In addition, the emotion engine analyzes users' emotional states in real time, understanding the overall emotional trends of consumers from sources such as social media, customer reviews, and call center inquiries. This emotional data is input into the demand forecasting model, influencing future demand forecasts. 【0700】 Furthermore, the server can use user sentiment data analyzed by the sentiment engine to predict the effectiveness of sales campaigns and promotions. This allows for the creation of inventory allocation plans that anticipate user responses in advance, enabling inventory management with a buffer to cope with sudden fluctuations in demand. 【0701】 As a concrete example, if the server detects an increase in customer reviews for a particular product using its sentiment engine, it reflects the potential for increased demand for that product in its demand forecasting model and secures additional inventory in advance. This coordination between forecasting and inventory allocation allows retailers, as users, to always provide customers with the products they need. 【0702】 Furthermore, users can provide feedback on sales strategies through the emotion engine and interface. This allows for a direct understanding of how to meet consumer needs and strengthens the overall inventory management strategy. In this way, the present invention achieves a higher level of inventory optimization by combining user emotion analysis with traditional inventory management. 【0703】 The following describes the processing flow. 【0704】 Step 1: 【0705】 The server collects historical sales information from each sales channel and stores it in a database. The collected data includes sales volume, sales period, customer attributes, and more. 【0706】 Step 2: 【0707】 The server uses the collected sales information to create a demand forecasting model and uses machine learning algorithms to improve the accuracy of the forecast. 【0708】 Step 3: 【0709】 The server uses an emotion engine to analyze user emotions from various sources, such as social media and review sites. This allows for an understanding of consumers' emotional state towards a product. 【0710】 Step 4: 【0711】 The server integrates sentiment data into the demand forecasting model and applies sentiment-based adjustments to further improve the accuracy of demand forecasts. The model reflects increases in positive sentiment towards the product in the forecasted demand. 【0712】 Step 5: 【0713】 The server calculates the optimal inventory allocation based on future demand forecasts and instructs each sales channel to apply it. Inventory allocation follows the results calculated from predicted demand and market sentiment trends. 【0714】 Step 6: 【0715】 The server monitors sales in real time and dynamically readjusts inventory allocation and distribution plans if a discrepancy is found between forecasts and actual sales. Sentiment data fluctuations are also re-evaluated during this process. 【0716】 Step 7: 【0717】 Users review reports generated by the server and incorporate them into sales strategies and inventory management policies. The results of sentiment analysis performed by the server are also used in strategic decision-making. 【0718】 Step 8: 【0719】 The device receives user feedback as needed and feeds that feedback back into both the emotion engine and the demand forecasting model. This improves the overall adaptability of the system. 【0720】 (Example 2) 【0721】 Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0722】 Traditional inventory management systems relied on sales data for demand forecasting, but they failed to adequately consider consumer sentiment and market trends, making it difficult to respond flexibly to fluctuations in demand. Furthermore, discrepancies between forecasting models and actual sales data could occur, hindering the optimization of inventory allocation. Therefore, there is a need for more accurate and flexible inventory management. 【0723】 The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. 【0724】 In this invention, the server includes means for collecting past transaction information from each supply route, means for training a demand forecasting algorithm based on the collected transaction information, and means for analyzing user sentiment information and reflecting the analysis results in the demand forecasting algorithm. By incorporating the emotional state of consumers into the demand forecast, it becomes possible to achieve more accurate demand forecasting and optimization of inventory allocation. 【0725】 "Supply chain" refers to the entire path a product takes from the manufacturer or distribution center to the consumer, and includes wholesalers, retailers, and online sales platforms. 【0726】 "Transaction information" refers to detailed data about the sale of a product, including information such as sales quantity, sales price, transaction date and time, and transaction region. 【0727】 A "demand forecasting algorithm" refers to a computational method or model used to predict future demand for a product based on collected data, enabling companies to rationally plan the necessary inventory and production volumes. 【0728】 "Emotional information" refers to data that indicates consumers' emotional states and emotional trends in the market, and is obtained from sources such as social media posts, customer reviews, and inquiries. 【0729】 "Learning" refers to the process by which an algorithm finds patterns and rules from the provided data and automatically updates the model to make highly accurate predictions. 【0730】 "Product allocation" refers to the process of appropriately allocating and supplying products to each sales location based on demand forecasts, and is an important activity for achieving efficient inventory management. 【0731】 "Assets" refer to all of the goods, property, and intellectual property owned by a company, and the management and optimization of these improve the operational efficiency of the company. 【0732】 "Discrepancy" refers to the difference between predicted demand and actual observed sales, and resolving this discrepancy leads to improved accuracy in inventory management. 【0733】 The embodiments for carrying out the invention are shown below. 【0734】 In this invention, the server integrates an inventory management system with an emotion engine that recognizes user emotions to achieve more accurate demand forecasting and optimized inventory allocation. Specifically, the server collects transaction information from each supply route and uses this information to train a demand forecasting algorithm. For training, it uses Python libraries for data analysis such as Pandas and Scikit-learn. Furthermore, it utilizes the emotion engine to analyze consumer emotion information in real time from various sources such as social media, customer reviews, and call center inquiries. For this analysis, it uses natural language processing libraries such as TensorFlow and NLTK. 【0735】 After transaction and sentiment data are analyzed, the server incorporates the sentiment data into a demand forecasting algorithm to predict future demand. Based on this forecast, the server adjusts product allocation to support efficient inventory management. The server also has the ability to constantly monitor the forecasting model and actual transaction data, and adjust product allocation as needed. 【0736】 For example, if consumer sentiment information about a particular cosmetic product rapidly gains positive reviews on social media, the server can use that data to predict the increase in demand and meet consumer needs by securing additional inventory in advance. In this way, retailers, as users, can provide consumers with the necessary products in a timely manner without missing sales opportunities. 【0737】 An example of a prompt to input into the generating AI model might be, "How can we build a demand forecasting model to optimize inventory allocation for each store?" This prompt allows for the development of new algorithms to improve demand forecasting accuracy. 【0738】 The flow of the specific processing in Example 2 will be explained using Figure 13. 【0739】 Step 1: 【0740】 The server collects historical transaction information from each supply chain. As input, it accesses online store and physical store sales databases to obtain detailed data such as product names, sales quantities, and sales periods. This data is extracted through database queries and stored on the server. As output, the collected transaction information is organized into usable datasets. 【0741】 Step 2: 【0742】 The server trains a demand forecasting algorithm based on the collected transaction information. The transaction data generated in Step 1 is used as input. The server uses libraries such as Pandas and Scikit-learn to analyze this data, extract features, and build a model suitable for demand forecasting. The trained demand forecasting model is obtained as output, which is useful for future demand forecasting. 【0743】 Step 3: 【0744】 The server analyzes user emotional information using an emotion engine. Inputs include social media posts, customer reviews, and call center inquiry logs. The server utilizes natural language processing techniques to score emotions as positive, negative, or neutral. TensorFlow and NLTK are used for this analysis. The output generates data indicating the user's emotional tendencies. 【0745】 Step 4: 【0746】 The server integrates the analyzed sentiment information into the demand forecasting model. The demand forecasting model obtained in step 2 and the sentiment data from step 3 are used as input. The server adjusts the model parameters to perform a more accurate demand forecast that reflects the sentiment data. The output is a demand forecast result that takes sentiment information into account. 【0747】 Step 5: 【0748】 The server optimizes product allocation and manages assets based on demand forecast results. The demand forecast results obtained in step 4 are used as input. The server calculates inventory reallocation and issues instructions to maintain optimal inventory levels at each sales point. The output is optimized product allocation, streamlining inventory management. 【0749】 Step 6: 【0750】 The user receives forecast results and sales strategy feedback from the server. The input consists of forecast data and analysis results generated by the server. The user uses this information to adjust sales activities and campaign plans. The output is that the user's sales strategies are aligned with market demand, maximizing sales opportunities. 【0751】 (Application Example 2) 【0752】 Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal". 【0753】 Modern inventory management systems generally forecast demand and manage inventory based on historical sales data, but they fail to take into account customer sentiment and the elusive trends of the market, making it difficult to respond immediately to fluctuations in demand. This increases the risk of oversupply or undersupply, hindering efficient inventory management. Furthermore, the lack of means to predict the effectiveness of sales strategies means that promotions and campaigns are not being adequately optimized. 【0754】 The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. 【0755】 In this invention, the server includes means for collecting historical sales data from each supply route, means for training a demand forecasting structure based on the collected sales data, and means for analyzing user sentiment data and integrating that sentiment data into the demand forecasting structure to improve the accuracy of demand. This enables advanced inventory management that incorporates customer sentiment and market trends. Furthermore, it enables immediate response to demand fluctuations through real-time monitoring of sales data and adjustment of supply allocation. 【0756】 "Supply route" refers to the concept of the path by which goods or services are delivered from the manufacturer or supplier to the consumer. 【0757】 "Sales data" refers to information that shows how much of a product or service was sold within a specific period, and typically includes quantity, price, and purchase date. 【0758】 A "demand forecast structure" refers to a statistical or computational model used to predict future demand levels based on historical data and market information. 【0759】 "Sentimental data" refers to information that reflects consumers' emotions and opinions, and is typically collected from sources such as social media, reviews, and survey results. 【0760】 "Inventory management" refers to the activities undertaken by companies and organizations to efficiently manage their inventory of goods and materials and to optimize the balance between supply and demand. 【0761】 A "sales strategy" refers to a plan or policy for effectively selling a product or service based on market and customer needs. 【0762】 This invention is an inventory management system that integrates sentiment data to improve demand forecasting. The system is implemented using a server, user terminals, and market information as a data source. 【0763】 The server collects historical sales data from each supply chain and uses this data to build a demand forecasting structure. The collected data undergoes a data cleaning process to prepare it for model training. During this process, data processing is performed using libraries such as Python's pandas and numpy. 【0764】 Next, natural language processing is performed to analyze user sentiment data. Sentiment data is obtained from social media posts and customer reviews, and positive / negative sentiment tendencies are evaluated using NLTK and TextBlob. This sentiment information is integrated as a feed into the demand forecasting structure, contributing to improving the accuracy of the model. 【0765】 The terminal receives recommended inventory allocations based on these analysis results, enabling real-time supply adjustments. It integrates with cloud computing services (e.g., AWS and Google Cloud) to perform dynamic data processing. 【0766】 As a concrete example, the system detects when a particular fashion brand gains attention on social media and predicts a surge in demand for that product category. If it determines there is a risk of inventory shortages, it immediately adjusts the supply allocation to increase the stock of the relevant product. 【0767】 The generative AI model can analyze sentiment data using the following prompt statements. 【0768】 "Collect recent tweets related to a specific product and analyze their sentiment scores." 【0769】 In this way, the server enables advanced inventory management to respond quickly to fluctuations in demand. 【0770】 The flow of a specific process in Application Example 2 will be explained using Figure 14. 【0771】 Step 1: 【0772】 The server collects historical sales data from each supply route. Inputs are database and sensor data from the supply route, and output is the collected raw data. Sales data is extracted from the database using SQL queries and stored in CSV or JSON format. 【0773】 Step 2: 【0774】 The server cleans the collected sales data and prepares it in a format suitable for training the demand forecasting model. The input is the raw data obtained in step 1, and the output is the prepared dataset. Missing value handling and outlier detection are performed using the Python pandas library. 【0775】 Step 3: 【0776】 The server collects user sentiment data from social media and customer reviews, and uses natural language processing to evaluate sentiment tendencies. The input is text from social media posts and reviews, and the output is a sentiment score. NLTK and TextBlob are used to analyze the text and calculate positive and negative scores. 【0777】 Step 4: 【0778】 The server integrates sentiment data into a demand forecasting model to improve its accuracy. The input is a prepared dataset and sentiment scores, and the output is an enhanced demand forecasting model. The machine learning library scikit-learn is used to retrain the model. 【0779】 Step 5: 【0780】 The terminal receives recommended inventory allocations based on an enhanced demand forecasting model. The input is forecast data from the enhanced demand forecasting model, and the output is the recommended inventory allocation. It communicates with the cloud system via a real-time API to retrieve the recommended allocation. 【0781】 Step 6: 【0782】 The user reviews the recommended inventory allocation and supply adjustment notifications on the terminal and makes adjustments as needed. The input is the recommended allocation from step 5, and the output is the actual inventory adjustment result. The user reviews the information provided through the terminal's UI and makes adjustments manually. 【0783】 The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data. 【0784】 Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. 【0785】 In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414. 【0786】 Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion. 【0787】 Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together. 【0788】 These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression. 【0789】 The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become. 【0790】 Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant. 【0791】 The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more." 【0792】 The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values. 【0793】 The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format. 【0794】 In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data. 【0795】 In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56. 【0796】 Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12. 【0797】 Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56. 【0798】 The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory. 【0799】 The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor. 【0800】 Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources. 【0801】 Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. 【0802】 The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above. 【0803】 All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference. 【0804】 The following is further disclosed regarding the embodiments described above. 【0805】 (Claim 1) 【0806】 A means of collecting past sales information from each sales channel, 【0807】 A means of training a demand forecasting model based on collected sales information, 【0808】 A means of predicting future demand using a trained demand forecasting model, 【0809】 A means for calculating inventory allocation based on predicted demand and optimizing inventory, 【0810】 A means of monitoring sales information in real time and adjusting inventory allocation when there is a discrepancy between forecasts and actual sales, 【0811】 A system that includes this. 【0812】 (Claim 2) 【0813】 The system according to claim 1, further comprising means for extracting feature quantities based on the characteristics of each sales channel. 【0814】 (Claim 3) 【0815】 The system according to claim 1, further comprising means for cleaning past data and preparing it in a format suitable for analysis. 【0816】 "Example 1" 【0817】 (Claim 1) 【0818】 A means of collecting past sales data from each distribution channel, 【0819】 A means of identifying sales trends by analyzing collected sales data, 【0820】 A means of constructing a demand forecasting model based on identified sales trends, 【0821】 A means of predicting future demand by utilizing a constructed demand forecasting model, 【0822】 A means for performing calculations to optimize inventory allocation based on estimated demand, 【0823】 A means of monitoring distribution information in real time and correcting inventory allocation when discrepancies arise between predictions and actual distribution, 【0824】 A system that includes this. 【0825】 (Claim 2) 【0826】 The system according to claim 1, further comprising means for extracting characteristic quantities based on the characteristics of each distribution channel. 【0827】 (Claim 3) 【0828】 The system according to claim 1, further comprising means for organizing past data and preparing it in a format suitable for analysis. 【0829】 "Application Example 1" 【0830】 (Claim 1) 【0831】 A means of collecting past sales information from each sales channel, 【0832】 A means of training a demand forecasting model based on collected sales information, 【0833】 A means of predicting future demand using a trained demand forecasting model, 【0834】 A means for calculating inventory allocation based on predicted demand and optimizing inventory, 【0835】 A means of monitoring sales information in real time and adjusting inventory allocation when there is a discrepancy between forecasts and actual sales, 【0836】 A means of generating inventory management warnings using a mobile information processing device and notifying sales managers, 【0837】 A system that includes this. 【0838】 (Claim 2) 【0839】 The system according to claim 1, further comprising means for extracting feature quantities based on the characteristics of each sales channel and displaying them on a mobile information processing device. 【0840】 (Claim 3) 【0841】 The system according to claim 1, further comprising means for cleaning past data, preparing it in a format suitable for analysis, and outputting it to a mobile information processing device. 【0842】 "Example 2 of combining an emotion engine" 【0843】 (Claim 1) 【0844】 A means of collecting past transaction information from each supply route, 【0845】 A means of training a demand forecasting algorithm based on collected transaction information, 【0846】 A means of predicting future demand using a trained demand forecasting algorithm, 【0847】 A means of analyzing user sentiment information and reflecting the analysis results in a demand forecasting algorithm, 【0848】 A means of calculating product allocation based on future demand and analyzed sentiment information, and optimizing assets, 【0849】 A means of monitoring transaction information in real time and adjusting product allocation when there is a discrepancy between predictions and actual transactions, 【0850】 A system that includes this. 【0851】 (Claim 2) 【0852】 The system according to claim 1, further comprising means for extracting characteristic information based on the characteristics of each supply route. 【0853】 (Claim 3) 【0854】 The system according to claim 1, further comprising means for purifying past data and preparing it in a format suitable for analysis. 【0855】 "Application example 2 when combining with an emotional engine" 【0856】 (Claim 1) 【0857】 A means of collecting historical sales data from each supply channel, 【0858】 A method for training a demand forecasting structure based on collected sales data, 【0859】 A means of predicting future demand using a learned demand forecasting structure, 【0860】 A means for calculating supply allocation based on predicted demand and optimizing inventory, 【0861】 A means of analyzing user sentiment data and integrating that sentiment data into a demand forecasting structure to improve the accuracy of demand forecasting, 【0862】 A means of monitoring sales data in real time and adjusting supply allocation when there is a discrepancy between forecasts and actual sales, 【0863】 A system that includes this. 【0864】 (Claim 2) 【0865】 The system according to claim 1, further comprising means for analyzing information from each supply route in order to evaluate the emotional tendencies of users. 【0866】 (Claim 3) 【0867】 The system according to claim 1, further comprising means for organizing historical data and adjusting it into a format suitable for analysis. [Explanation of Symbols] 【0868】 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

[Claim 1] A means of collecting past sales information from each sales channel, A means of training a demand forecasting model based on collected sales information, A means of predicting future demand using a trained demand forecasting model, A means for calculating inventory allocation based on predicted demand and optimizing inventory, A means of monitoring sales information in real time and adjusting inventory allocation when there is a discrepancy between forecasts and actual sales, A system that includes this. [Claim 2] The system according to claim 1, further comprising means for extracting feature quantities based on the characteristics of each sales channel. [Claim 3] The system according to claim 1, further comprising means for cleaning past data and preparing it in a format suitable for analysis.

Images